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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     рассказал
    0.49
     poitrine
    0.48
     gelungen
    0.47
     каких
    0.47
     McLaughlin
    0.47
     Rho
    0.46
    ին
    0.46
    ନ୍ତ
    0.46
    给
    0.46
    ක්ෂ
    0.46
    POSITIVE LOGITS
     absor
    0.51
     س
    0.45
    mey
    0.44
    nger
    0.44
     وما
    0.43
     exig
    0.43
    noon
    0.43
     arbete
    0.42
     ولم
    0.41
     நிர
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.