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

    Neuronpedia

    INDEX
    Explanations

    mathematical and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    运营
    0.63
    制作
    0.60
     운영
    0.55
     콘텐츠
    0.53
    sponsor
    0.52
     오픈
    0.52
     impoz
    0.51
     스타
    0.51
     asesor
    0.50
    recomend
    0.50
    POSITIVE LOGITS
     정의역
    0.66
     Riemann
    0.61
     Frobenius
    0.58
     Lebesgue
    0.57
    を表
    0.57
    変数
    0.57
     함수
    0.57
     величина
    0.57
     Banach
    0.56
    집합
    0.56
    Act Density 0.002%

    No Known Activations