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

    Neuronpedia

    INDEX
    Explanations

    math functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    其他
    -0.07
    Mode
    -0.07
     Temporary
    -0.07
    ura
    -0.06
     squirrel
    -0.06
     kwargs
    -0.06
    Sleep
    -0.06
    -inner
    -0.06
    лены
    -0.06
     employs
    -0.06
    POSITIVE LOGITS
     columnName
    0.07
    _sent
    0.07
     gấp
    0.07
    מ
    0.07
     corro
    0.07
     rollback
    0.06
     vừa
    0.06
    .mousePosition
    0.06
    用品
    0.06
    DIFF
    0.06
    Act Density 0.022%

    No Known Activations