AutoML does not provide any support for model interpretability, as it focuses solely on model performance.

AutoML provides limited support for model interpretability by generating a summary of the model's features and their importance.

AutoML supports model interpretability by using techniques such as feature importance ranking, partial dependence plots, and SHAP values to explain the decision-making process of the models it generates.

AutoML supports model interpretability by providing a detailed breakdown of the model's architecture and hyperparameters, but not by explaining the decision-making process.