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

    Neuronpedia

    INDEX
    Explanations

    say "al" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    心智
    -0.07
    unlink
    -0.07
    NSString
    -0.06
    省政府
    -0.06
    _Matrix
    -0.06
    @endsection
    -0.06
    خيل
    -0.06
    <Real
    -0.06
    之初
    -0.06
    .getFloat
    -0.06
    POSITIVE LOGITS
    褶
    0.08
     interruptions
    0.07
    Prom
    0.07
     upgraded
    0.07
     prostitu
    0.06
     ang
    0.06
     argues
    0.06
    工业园区
    0.06
    Ст
    0.06
     argued
    0.06
    Act Density 0.002%

    No Known Activations