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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    שׁ
    0.76
    ש
    0.73
    abundance
    0.69
    전
    0.67
    ורים
    0.67
     열
    0.66
    iter
    0.66
    ulatus
    0.66
    워
    0.65
    וד
    0.65
    POSITIVE LOGITS
     cuesta
    0.82
     hir
    0.80
    ceff
    0.79
     registro
    0.78
    كينا
    0.78
     caminos
    0.77
     crawl
    0.76
     युव
    0.76
     llevan
    0.76
     bier
    0.75
    Act Density 0.000%

    No Known Activations