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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     дет
    -0.09
    ישה
    -0.08
    ーシ
    -0.07
    .left
    -0.07
    instein
    -0.07
    Ǐ
    -0.07
    宇宙
    -0.07
    放入
    -0.07
    展开
    -0.07
     Spaces
    -0.07
    POSITIVE LOGITS
     Fahr
    0.08
    ﮪ
    0.07
     $$
    0.06
    hythm
    0.06
    *****/↵
    0.06
     Bapt
    0.06
    反腐倡
    0.06
    mund
    0.06
     bye
    0.06
    닪
    0.06
    Act Density 0.003%

    No Known Activations