Jannik Brinkmann is a Ph.D. student in Computer Science at the Technical University of Clausthal since 2025. He began his doctoral studies at the University of Mannheim in 2022 and continued at Clausthal when his advisor, Prof. Christian Bartelt, moved there. His research focuses on mechanistic interpretability, safety, and reasoning in large language models, with a particular interest in understanding how neural networks represent and process information. He has held visiting researcher positions at Northeastern University and the NYU Center for Data Science, where he collaborated with leading groups on natural language processing and interpretability. His work has been published at top conferences including NeurIPS, ICLR, ACL, NAACL, and ICCV. His contributions have been recognized with an Honorable Mention for Best Paper at the ICML 2024 Workshop on Mechanistic Interpretability, and a NeurIPS 2024 Outstanding Reviewer Award. His research has been supported by a grant from the Long-Term Future Fund.
Personal website: jannikbrinkmann.com