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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     appréci
    0.55
     والم
    0.53
     кем
    0.50
     pokry
    0.50
     protégé
    0.50
     e
    0.49
     pemb
    0.49
     როგორც
    0.49
     desempe
    0.48
     bä
    0.48
    POSITIVE LOGITS
    上げる
    0.51
    Basketball
    0.49
    Trying
    0.48
    ５
    0.48
    Beef
    0.46
    Tian
    0.46
    ጠን
    0.46
    рость
    0.46
    GOING
    0.45
    Panic
    0.45
    Act Density 0.002%

    No Known Activations