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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isex
    0.66
    抽象
    0.66
    នាំ
    0.61
     unge
    0.61
    同意
    0.60
    ↵
    0.59
    適用
    0.59
     agnostic
    0.59
    ra
    0.58
    由
    0.58
    POSITIVE LOGITS
     പക്ഷേ
    0.88
     ώστε
    0.79
     ന
    0.73
     ή
    0.71
     perder
    0.70
     hoặc
    0.70
     Алла
    0.70
     rápido
    0.69
    өм
    0.69
    ӓ
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.