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

    Neuronpedia

    INDEX
    Explanations

    Code queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _scripts
    -0.08
    цвет
    -0.07
     kayak
    -0.06
    ipline
    -0.06
     관심
    -0.06
    .NotFound
    -0.06
    means
    -0.06
     tisk
    -0.06
    Become
    -0.06
     CMP
    -0.06
    POSITIVE LOGITS
     Sw
    0.07
    ิจกรรม
    0.06
     مط
    0.06
    emas
    0.06
    spec
    0.06
    -data
    0.06
     �
    0.06
     believing
    0.06
     الوط
    0.06
    (me
    0.06
    Act Density 0.003%

    No Known Activations