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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ൭
    0.47
     leçon
    0.45
    inairement
    0.43
    ሎጂ
    0.43
    તે
    0.42
    थरूम
    0.42
     ഹിന്ദു
    0.41
    त्रियों
    0.40
    线的
    0.40
     ইয়াহিয়ার
    0.40
    POSITIVE LOGITS
    '
    0.46
     braz
    0.45
     comun
    0.43
     nati
    0.42
     and
    0.41
     RU
    0.40
    '*
    0.39
     inqu
    0.39
    sep
    0.39
    тели
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.