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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Kees
    0.47
    습니다
    0.42
    六年
    0.42
    文書
    0.41
     an
    0.41
     econôm
    0.40
     Kxg
    0.39
     acumen
    0.39
     지난해
    0.38
     شرح
    0.38
    POSITIVE LOGITS
    ান
    0.45
    across
    0.45
     різні
    0.45
    bedrooms
    0.44
    Ј
    0.44
     ranging
    0.44
     квіт
    0.43
    Levels
    0.43
     trajets
    0.42
     situaciones
    0.42
    Act Density 0.004%

    No Known Activations