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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dozen
    1.31
    coln
    1.26
     tốt
    1.07
    貫
    1.07
     bulletin
    1.07
    ῳ
    1.04
    称为
    1.03
    ">→</
    1.03
     true
    1.03
    という意味
    1.03
    POSITIVE LOGITS
     Packed
    1.20
    مة
    1.19
    ljivo
    1.16
    nya
    1.11
    de
    1.09
    اے
    1.09
     एजेंट
    1.07
    ㈤
    1.07
     Nesta
    1.06
    ायचे
    1.06
    Act Density 0.000%

    No Known Activations