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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cancellation
    -0.08
    ancellation
    -0.08
    arial
    -0.07
    imestamp
    -0.07
    Ï
    -0.07
    치는
    -0.07
     doesn
    -0.07
    -au
    -0.06
     proven
    -0.06
    -In
    -0.06
    POSITIVE LOGITS
     {"
    0.07
     [`
    0.06
    _paint
    0.06
    :self
    0.06
    :Set
    0.06
     šk
    0.06
    *self
    0.06
     ÜNİ
    0.06
     resolving
    0.06
    yses
    0.06
    Act Density 0.004%

    No Known Activations