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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Domestic
    0.55
    ：
    0.54
    Its
    0.52
    Rec
    0.50
    सिव
    0.50
    Sobre
    0.49
    Lyric
    0.49
    Personally
    0.48
    Desk
    0.48
    Solo
    0.48
    POSITIVE LOGITS
     существуют
    0.64
     существует
    0.62
     есть
    0.61
     понятие
    0.60
     אין
    0.59
     nėra
    0.58
     există
    0.57
     нет
    0.57
     esiste
    0.56
     είναι
    0.55
    Act Density 0.129%

    No Known Activations