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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lookahead
    -0.08
    勤劳
    -0.07
    セックス
    -0.07
    😰
    -0.07
    @Entity
    -0.07
     signatures
    -0.06
     newIndex
    -0.06
     Curt
    -0.06
    ること
    -0.06
    مؤسسات
    -0.06
    POSITIVE LOGITS
    至于
    0.07
    probe
    0.06
     promoting
    0.06
    Ads
    0.06
    iams
    0.06
     tập
    0.06
    诸如
    0.06
    🚾
    0.06
    başı
    0.06
    从此
    0.06
    Act Density 0.154%

    No Known Activations