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

    Neuronpedia

    INDEX
    Explanations

    ervised

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     설치
    -0.07
     geçmiş
    -0.07
    798
    -0.07
    番号
    -0.07
     gown
    -0.07
     ном
    -0.07
    Bounds
    -0.07
    Shows
    -0.07
    ;padding
    -0.07
     عد
    -0.07
    POSITIVE LOGITS
    Пр
    0.07
     nội
    0.06
    ervised
    0.06
     presently
    0.06
    __':
↵
    0.06
     waste
    0.06
    [col
    0.06
    _IL
    0.05
     revamped
    0.05
    #{
    0.05
    Act Density 0.004%

    No Known Activations