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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ger
    0.51
    h
    0.41
     package
    0.41
     Кроме
    0.40
    πά
    0.40
     Wage
    0.39
    lo
    0.38
    ED
    0.38
     Guerra
    0.37
    ло
    0.37
    POSITIVE LOGITS
     مشکلات
    0.58
    iation
    0.50
    멋
    0.49
    acją
    0.48
     opérations
    0.48
     اشک
    0.47
    ಿನ
    0.46
     ခ
    0.46
    شارات
    0.46
     اللہ
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.