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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    クトル
    0.47
     Eles
    0.41
    信仰
    0.40
     unregulated
    0.40
    чных
    0.40
     Fate
    0.40
    的重要性
    0.40
     Gordo
    0.39
    ভো
    0.39
    ヴォ
    0.39
    POSITIVE LOGITS
    was
    0.45
    ò
    0.44
     טי
    0.40
    super
    0.40
     tourn
    0.39
    ”
    0.39
    the
    0.39
     startup
    0.39
     ogen
    0.39
     tram
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.