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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝗗
    0.79
     τῶν
    0.77
     Перейти
    0.77
    ចុ
    0.77
     oleh
    0.76
     ابھی
    0.75
    に使用
    0.75
     між
    0.75
    に係る
    0.75
     Relating
    0.74
    POSITIVE LOGITS
    .
    0.76
    iyi
    0.75
    ING
    0.71
     मठ
    0.70
    шего
    0.69
     colitis
    0.67
     않습니다
    0.66
     العافيه
    0.65
    甜
    0.63
    ς
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.