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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ؛
    0.77
    ستخدم
    0.73
    ﺔ
    0.72
    ៖
    0.70
    ޏ
    0.69
     ။
    0.68
     ؛
    0.68
     }{}_{\
    0.68
     ܗ
    0.66
     Buchstaben
    0.66
    POSITIVE LOGITS
    ・
    0.61
    企業
    0.59
    、
    0.59
     nhất
    0.58
    도
    0.58
    地
    0.57
     personnels
    0.56
    의
    0.56
     인
    0.55
     entreprise
    0.54
    Act Density 0.004%

    No Known Activations