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

    Neuronpedia

    INDEX
    Explanations

    filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有点
    -0.07
     trưởng
    -0.07
     nacional
    -0.06
     التو
    -0.06
     Lawyer
    -0.06
     getStatus
    -0.06
    western
    -0.06
     alo
    -0.06
    كال
    -0.06
     announces
    -0.06
    POSITIVE LOGITS
    PTS
    0.08
     convenience
    0.06
    ژه
    0.06
    Nonnull
    0.06
    dio
    0.06
    inactive
    0.06
     itu
    0.06
    nda
    0.06
    İ
    0.06
    lama
    0.06
    Act Density 0.000%

    No Known Activations