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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gelungen
    0.50
    ନ୍ତ
    0.48
     рассказал
    0.47
    ին
    0.47
    密切
    0.47
     poitrine
    0.46
    给
    0.46
     каких
    0.46
     McLaughlin
    0.46
    সাব
    0.45
    POSITIVE LOGITS
     absor
    0.50
    noon
    0.44
     س
    0.43
    nger
    0.42
    mey
    0.41
     exig
    0.40
     arbete
    0.40
     و
    0.39
     دائ
    0.39
     వరకు
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.