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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    OUND
    0.78
    U
    0.76
    EN
    0.74
    مين
    0.70
    ين
    0.67
    hua
    0.67
    ئة
    0.67
     knn
    0.66
    ﻴ
    0.66
    రిత్ర
    0.65
    POSITIVE LOGITS
    といった
    0.75
     semangat
    0.73
     допо
    0.70
     ماند
    0.70
    ophobia
    0.69
     வழங்கு
    0.68
    arası
    0.66
     সমূহ
    0.65
     vog
    0.65
     வழங்கும்
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.