Deep neural networks, while effective in solving complex problems, are often perceived as "black boxes", limiting their adoption in contexts where transparency and explainability are crucial. This lack of visibility raises ethical and legal concerns, particularly in critical areas such as security, where automated decisions can have significant consequences. The implementation of the General Data Protection Regulation (GDPR) emphasizes the importance of justifying decisions made by these systems. In this work, we explore the use of visualization techniques to improve the understanding of anomaly detection models based on convolutional recurrent neural networks (CNN + RNN), integrating a TimeDistributed layer. Our model combines VGG19 for convolutional feature extraction and a GRU layer for sequential analysis to process real-time video data. Although this approach is suitable for models dealing with temporal data, it complicates gradient propagation since each element of the sequence is processed independently. The TimeDistributed layer applies a model or layer to each element of the sequence, but unfortunately, this structure dissociates temporal information, which can make it difficult to associate gradients with specific elements of the sequence. Therefore, we attempt to adapt visualization techniques, such as saliency maps and Grad-CAM, to make them applicable to models incorporating a temporal dimension. This article highlights current challenges in the visual interpretation of models that handle video data. While specific methods for video are still limited, it demonstrates the possibility of adapting visualization techniques designed for static images to neural network architectures processing video sequences. This approach extends the use of common interpretation methods from classical convolutional networks to recurrent convolutional networks and video data, thus offering a transitional solution in the absence of dedicated techniques.