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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ገኛ
    0.36
    וכ
    0.33
     информа
    0.33
     코드
    0.33
    赤ちゃん
    0.33
    Все
    0.33
    慝
    0.31
     জীববিজ্ঞান
    0.31
    yczne
    0.31
     вся
    0.30
    POSITIVE LOGITS
    the
    0.31
     ardından
    0.31
     যেটি
    0.30
     Northern
    0.29
     serta
    0.29
     Tham
    0.29
     Dalam
    0.28
     Pirates
    0.28
     North
    0.28
    不错的
    0.28
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.