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

    Neuronpedia

    INDEX
    Explanations

    personality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -inspired
    -0.07
     participants
    -0.06
     initiatives
    -0.06
    accel
    -0.06
    iska
    -0.06
    /media
    -0.06
     Challenge
    -0.06
    getitem
    -0.06
    UnitOfWork
    -0.06
    墓
    -0.06
    POSITIVE LOGITS
     evaluator
    0.08
    0.07
    0.07
     Character
    0.06
     PID
    0.06
    ovali
    0.06
     Rename
    0.06
    _kill
    0.06
    ULD
    0.06
     slic
    0.06
    Act Density 0.006%

    No Known Activations