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

    Neuronpedia

    INDEX
    Explanations

    time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     submodule
    -0.06
     Syracuse
    -0.06
     Buffy
    -0.06
    _KIND
    -0.06
    ------+
    -0.06
     alcoholic
    -0.06
     Parameters
    -0.06
    焼
    -0.06
     Kenneth
    -0.06
     màu
    -0.06
    POSITIVE LOGITS
    гар
    0.07
    _cg
    0.07
    др
    0.06
    ЕС
    0.06
    С
    0.06
    >A
    0.06
    خذ
    0.06
     дітей
    0.06
    -badge
    0.06
    ंपन
    0.06
    Act Density 0.021%

    No Known Activations