Mental health analysis from social media text demands both high accuracy and interpretability for responsible healthcare applications. This paper explores Kolmogorov Arnold Networks (KANs) for mental health detection and classification, demonstrating their superior performance compared to Multi-Layer Perceptrons (MLPs) in accuracy while requiring fewer parameters. To further enhance interpretability, we leverage the Local Interpretable Model Agnostic Explanations (LIME) method to identify key features, resulting in a simplified KAN model. This allows us to derive governing equations for each class, providing a deeper understanding of the relationships between texts and mental health conditions.