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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    are
    0.80
    ad
    0.75
    7
    0.71
    註
    0.70
    1
    0.68
    자
    0.68
    art
    0.67
    aughters
    0.67
    entral
    0.65
    irar
    0.64
    POSITIVE LOGITS
     kebab
    0.89
    ی
    0.86
     napis
    0.84
     Nhi
    0.82
     melihat
    0.82
     এছাড়াও
    0.80
     lainnya
    0.79
     mahasiswa
    0.77
     flavoured
    0.77
     andere
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.