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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ?
    0.68
    過了
    0.66
    过了
    0.63
    юнча
    0.62
    の場合は
    0.61
     بالنسبة
    0.60
    South
    0.59
     ከሆነ
    0.58
    ével
    0.58
     위해서
    0.58
    POSITIVE LOGITS
     to
    1.55
     να
    1.26
    ที่จะ
    1.03
     upang
    0.87
    ທີ່ຈະ
    0.86
    to
    0.85
    ToSend
    0.80
    ToRemove
    0.79
     להיות
    0.78
    에게
    0.77
    Act Density 0.027%

    No Known Activations