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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Suf
    0.45
     klimat
    0.45
     U
    0.44
     kcal
    0.44
     Ernährung
    0.44
    häuse
    0.44
     питания
    0.44
     abge
    0.43
     sepsis
    0.43
     penilaian
    0.43
    POSITIVE LOGITS
    ك
    0.58
    ク
    0.57
    ف
    0.55
    비
    0.54
    ਕਰ
    0.52
    і
    0.52
    글
    0.51
    પ્ર
    0.49
    遨
    0.49
    ኩል
    0.48
    Act Density 0.000%

    No Known Activations