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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ඒවා
    0.80
    ؛
    0.77
    ูนย์
    0.75
    𝗸
    0.75
    ﺖ
    0.74
     أو
    0.73
     يت
    0.72
    ور
    0.71
     ሽፋ
    0.70
     ซึ่ง
    0.70
    POSITIVE LOGITS
    자
    0.84
    이
    0.72
    지
    0.71
    정
    0.71
    가
    0.68
    나
    0.68
     소
    0.67
    인
    0.67
    상
    0.66
    보
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.