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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cop
    -0.07
    view
    -0.07
    986
    -0.07
    duc
    -0.06
    _hid
    -0.06
     Uhr
    -0.06
    jualan
    -0.06
     Bah
    -0.06
    Cop
    -0.06
    арамет
    -0.06
    POSITIVE LOGITS
     откры
    0.06
    겼
    0.06
    .axis
    0.06
    uses
    0.06
     под
    0.06
    /save
    0.06
    .Please
    0.06
    .NOT
    0.06
    usions
    0.06
     suspend
    0.06
    Act Density 0.018%

    No Known Activations