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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    God
    -0.07
    ủ
    -0.07
     Legal
    -0.07
     highlight
    -0.06
     Mom
    -0.06
     plausible
    -0.06
     Friendly
    -0.06
    Week
    -0.06
    \[
    -0.06
     BU
    -0.06
    POSITIVE LOGITS
    yon
    0.07
    cba
    0.07
    采用
    0.07
     PyObject
    0.07
    _FAMILY
    0.07
     yönetim
    0.06
     subtype
    0.06
     फ
    0.06
    iscard
    0.06
     한국
    0.06
    Act Density 0.112%

    No Known Activations