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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     confronts
    0.44
    살
    0.40
     земель
    0.39
    国土
    0.38
    土地
    0.37
     нельзя
    0.37
    ☠
    0.37
     フ
    0.36
     phúc
    0.36
     الفر
    0.36
    POSITIVE LOGITS
     acara
    0.45
     recevoir
    0.44
     indicating
    0.43
     Essen
    0.43
     eset
    0.42
     Academia
    0.42
     espes
    0.41
     Spreadsheet
    0.41
    有一个
    0.41
     bebé
    0.41
    Act Density 0.004%

    No Known Activations