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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     NASCAR
    -0.07
     consumes
    -0.06
     empath
    -0.06
     מאח
    -0.06
     федер
    -0.06
     carousel
    -0.06
     useSelector
    -0.06
     khẳng
    -0.06
    깐
    -0.06
     Dota
    -0.06
    POSITIVE LOGITS
    �
    0.07
    妄
    0.06
    ирование
    0.06
    ANGE
    0.06
    يات
    0.06
    上了
    0.06
    write
    0.06
     rồi
    0.06
    שיעור
    0.06
     Bbw
    0.06
    Act Density 0.055%

    No Known Activations