Nordic AI Safety Lab | Interpretability-informed control for AI safety

Nordic AI Safety Lab

The Nordic AI Safety Lab at the University of Southern Denmark develops methods to understand and control AI systems. We believe that interpretability—understanding the internal mechanisms of AI—is essential for achieving meaningful control and ensuring safety. Our research focuses on areas such as interpretability & transparency, agentic & multi-agent safety, and control & containment.

Learn more

Contact us via nordicaisafetylab@lpag.de