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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ן
    0.78
    as
    0.77
    rar
    0.73
    il
    0.72
    ا
    0.66
    л
    0.65
    ak
    0.61
    на
    0.61
    0.59
    Defendant
    0.58
    POSITIVE LOGITS
     tolu
    1.01
    меча
    0.99
     vermel
    0.93
    ționale
    0.91
    녕하세요
    0.90
     bicicletas
    0.89
     rostr
    0.89
    পাত্র
    0.88
     mercados
    0.88
     peralatan
    0.88
    Act Density 0.001%

    No Known Activations