Alexander Gitnik is a student researcher at the Explainable Machine Learning Group and the Max Planck Institute for Informatics, under the supervision of Prof. Zeynep Akata and Prof. Bernt Schiele. He is currently pursuing his Bachelor’s degree in Computer Science at TUM, with an exchange stay at Korea University. His primary research interests center around mechanistic interpretability of neural networks, focusing on understanding learned representations and developing interpretable deep learning models.