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
     ArgumentError
    -0.07
    Copyright
    -0.07
     постро
    -0.06
    �
    -0.06
    _h
    -0.06
     AW
    -0.06
     ş
    -0.06
     veri
    -0.05
    Logger
    -0.05
    かし
    -0.05
    POSITIVE LOGITS
    搜
    0.07
    تن
    0.07
    --↵
    0.07
     heating
    0.07
     divider
    0.06
    rary
    0.06
     NES
    0.06
     Sleep
    0.06
    itimate
    0.06
     ")
    0.06
    Act Density 0.001%

    No Known Activations