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

    Neuronpedia

    INDEX
    Explanations

    special

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     구성
    -0.08
    .toolStrip
    -0.07
     отп
    -0.07
    ordum
    -0.07
     bě
    -0.07
    播
    -0.07
    .ButterKnife
    -0.07
     Tabs
    -0.07
    半
    -0.06
    -purple
    -0.06
    POSITIVE LOGITS
    нося
    0.06
    َي
    0.06
    SQLException
    0.06
     motiv
    0.06
    ?id
    0.06
     exc
    0.06
     Wellness
    0.06
     مدل
    0.06
    /stat
    0.06
     mechan
    0.06
    Act Density 0.006%

    No Known Activations