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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     piensan
    0.62
    ﺖ
    0.57
    ность
    0.56
     mengurangi
    0.56
     الخاصة
    0.55
     varía
    0.55
    ﺤ
    0.54
     quieren
    0.52
     realice
    0.52
     prévue
    0.52
    POSITIVE LOGITS
    ات
    0.68
     on
    0.61
    s
    0.61
    al
    0.61
    est
    0.60
    ast
    0.60
     in
    0.59
    il
    0.59
     for
    0.59
     to
    0.58
    Act Density 0.000%

    No Known Activations