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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     desiderio
    0.78
     desenvolved
    0.73
     garagem
    0.73
     podataka
    0.71
    ա
    0.71
     diri
    0.71
     personenbez
    0.70
    দ্দ
    0.70
     جنبي
    0.70
     diejenigen
    0.69
    POSITIVE LOGITS
    L
    0.86
    LQ
    0.80
    R
    0.76
    C
    0.74
    要有
    0.71
    al
    0.68
    RNN
    0.68
    RQ
    0.68
    ଣ୍
    0.67
    顾
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.