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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    捃
    -0.08
    /remove
    -0.08
    (div
    -0.07
    (mi
    -0.07
    (fi
    -0.07
    verification
    -0.07
    [Y
    -0.07
    أسب
    -0.07
    Sites
    -0.07
    (sl
    -0.07
    POSITIVE LOGITS
    IŞ
    0.08
     "',
    0.07
    同事们
    0.07
     honor
    0.07
    حقيقة
    0.07
    Xã
    0.07
     poniew
    0.07
    换届
    0.06
    ﲨ
    0.06
    Freedom
    0.06
    Act Density 0.001%

    No Known Activations