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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RowBox
    -0.07
    ارا
    -0.06
    文化
    -0.06
     civil
    -0.06
     useDispatch
    -0.06
     ย
    -0.06
     predicts
    -0.06
    \common
    -0.06
    작
    -0.06
    inkel
    -0.06
    POSITIVE LOGITS
     }),
    0.08
    ultimo
    0.07
    _VERTICAL
    0.07
    gua
    0.07
     ترب
    0.06
     invent
    0.06
    cept
    0.06
     فقط
    0.06
     perpetrator
    0.06
    <Void
    0.06
    Act Density 0.005%

    No Known Activations