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

    Neuronpedia

    INDEX
    Explanations

    internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    юк
    -0.06
    ケ
    -0.06
     né
    -0.06
    كات
    -0.06
    т
    -0.06
    ी-
    -0.06
    ewish
    -0.06
     Nairobi
    -0.06
    Fi
    -0.06
    建設
    -0.06
    POSITIVE LOGITS
    -dismiss
    0.07
    _tran
    0.07
    amacare
    0.06
     courage
    0.06
     дж
    0.06
     avanz
    0.06
    -leading
    0.06
    _sentences
    0.06
     honesty
    0.06
     '^
    0.06
    Act Density 0.002%

    No Known Activations