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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    са
    0.49
    се
    0.48
    е
    0.47
    im
    0.47
    ειο
    0.45
    й
    0.44
    en
    0.43
    á
    0.42
    со
    0.42
    но
    0.42
    POSITIVE LOGITS
     每个
    0.85
     didnt
    0.80
     调用
    0.80
     doesnt
    0.78
     দ্বারা
    0.77
     用于
    0.72
    <unused2167>
    0.71
    ﻐ
    0.70
     ಮತ್ತು
    0.70
     हमको
    0.70
    Act Density 5.351%

    No Known Activations