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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reinvest
    0.42
     bedside
    0.39
     вернуться
    0.38
    DN
    0.37
     واپس
    0.37
    ادم
    0.37
     возвра
    0.37
     thái
    0.37
     dims
    0.37
     penc
    0.36
    POSITIVE LOGITS
    背
    2.08
     backs
    1.92
     Rücken
    1.73
     背
    1.69
     lưng
    1.49
     espalda
    1.45
     dorsal
    1.33
    backed
    1.31
    backs
    1.30
     спине
    1.28
    Act Density 0.017%

    No Known Activations