Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Movement or transition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (n
    -0.07
    haling
    -0.07
     wek
    -0.07
    itrine
    -0.07
    ىتى
    -0.07
     testing
    -0.07
     strategi
    -0.07
     ventre
    -0.07
     {↵↵
    -0.07
     распис
    -0.07
    POSITIVE LOGITS
     portability
    0.13
     transfér
    0.12
     Across
    0.12
     portable
    0.11
     transferable
    0.11
    portable
    0.11
    Across
    0.11
     seamlessly
    0.11
     continuity
    0.11
     Saves
    0.10
    Act Density 0.045%

    No Known Activations