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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ni
    0.69
    ො
    0.64
     etiqu
    0.63
    ﺷ
    0.63
    偏差
    0.63
    الغ
    0.62
    而且
    0.61
    ﻳ
    0.61
    crocodile
    0.60
    提到的
    0.60
    POSITIVE LOGITS
     비롯
    0.85
     보니
    0.77
     storefront
    0.73
    icrous
    0.71
    툼
    0.70
     whatnot
    0.68
    த்தைக்
    0.67
    anato
    0.67
     რაც
    0.67
    Pricing
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.