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

    Neuronpedia

    INDEX
    Explanations

    DAMAGES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (...)
    -0.07
     확
    -0.07
     MATRIX
    -0.06
     موج
    -0.06
    ,:)
    -0.06
     вимог
    -0.06
     qualification
    -0.06
    紹介
    -0.06
     helfen
    -0.06
     页面
    -0.06
    POSITIVE LOGITS
     DAMAGES
    0.11
    ()+"
    0.07
     brains
    0.06
    Drag
    0.06
    _nil
    0.06
     firearms
    0.06
    InterruptedException
    0.06
     Romans
    0.06
     crus
    0.06
     Rehabilitation
    0.06
    Act Density 0.000%

    No Known Activations