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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nancy
    -0.08
     slap
    -0.08
    nprintf
    -0.08
     Romney
    -0.08
    _FORE
    -0.08
     посел
    -0.08
    mallow
    -0.08
    logan
    -0.08
     بحسب
    -0.08
    <!--[
    -0.08
    POSITIVE LOGITS
    Types
    0.08
    の場合
    0.08
    (?)
    0.08
     (?)
    0.08
    ‌ల
    0.08
    Applic
    0.07
     ๆ
    0.07
    _types
    0.07
     Availability
    0.07
    ，否则
    0.07
    Act Density 0.073%

    No Known Activations