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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     الم
    2.39
     مع
    2.33
     تم
    2.26
     سوف
    2.11
     regarded
    2.09
     נ
    2.09
     ن
    2.04
     ر
    2.04
     بال
    2.04
    ّ
    2.03
    POSITIVE LOGITS
     다른
    2.57
     지난
    2.48
     이
    2.47
     기존
    2.44
     처음
    2.42
     지난해
    2.41
     일반
    2.40
     다양한
    2.37
     가능한
    2.35
     어느
    2.33
    Act Density 0.016%

    No Known Activations