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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ين
    1.98
    т
    1.91
    ت
    1.80
    ं
    1.65
    вам
    1.63
    ுமா
    1.62
    t
    1.62
    ons
    1.61
    ే
    1.59
    ai
    1.56
    POSITIVE LOGITS
     jantung
    1.77
    اعر
    1.68
    ことになる
    1.64
     Tháng
    1.59
     وعلى
    1.58
    郄
    1.57
    नेटिक
    1.56
    OU
    1.55
     جمعیت
    1.54
    الم
    1.53
    Act Density 1.719%

    No Known Activations