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

    Neuronpedia

    INDEX
    Explanations

    Petrov names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     previously
    -0.07
     mechanic
    -0.07
    .Attributes
    -0.07
     traditionally
    -0.07
     styled
    -0.07
     लगाने
    -0.07
    оно
    -0.07
    mathrm
    -0.06
    _prom
    -0.06
     Mess
    -0.06
    POSITIVE LOGITS
     buong
    0.09
    Resposta
    0.09
     الاتفاق
    0.08
     Arqu
    0.08
    ANK
    0.08
     jalan
    0.08
    راز
    0.08
     адказ
    0.08
     khut
    0.08
    estrutura
    0.08
    Act Density 0.000%

    No Known Activations