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

    Neuronpedia

    INDEX
    Explanations

    E

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SIM
    -0.07
    .Rendering
    -0.07
     '#
    -0.07
     Дж
    -0.07
     Cookies
    -0.07
    kv
    -0.07
    /GL
    -0.07
     ž
    -0.07
    خص
    -0.07
    .parametrize
    -0.07
    POSITIVE LOGITS
    🎊
    0.08
    Values
    0.07
     springs
    0.07
    ょう
    0.07
    ጔ
    0.07
    领导
    0.07
    ₥
    0.07
    Evento
    0.07
    תשובות
    0.07
    \Message
    0.07
    Act Density 0.001%

    No Known Activations