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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     zwei
    0.86
    льный
    0.84
     первый
    0.84
     drei
    0.82
    ⊹
    0.80
    ار
    0.80
     новый
    0.79
     permiso
    0.79
    trab
    0.79
     unang
    0.79
    POSITIVE LOGITS
    ب
    0.82
     nonostante
    0.77
    시에
    0.73
    로서
    0.73
    ;$
    0.71
     malgré
    0.70
    فض
    0.70
    іл
    0.70
    𝘨
    0.70
     publiques
    0.70
    Act Density 0.000%

    No Known Activations