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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    criar
    1.09
     impide
    1.07
    ールの
    1.02
    ды
    0.99
     процесса
    0.98
    ği
    0.97
    puede
    0.97
    сыз
    0.97
     fenô
    0.96
    ซิตี
    0.96
    POSITIVE LOGITS
     classes
    0.92
    .
    0.88
    /
    0.88
    classes
    0.71
     i
    0.71
     worth
    0.69
     braiding
    0.69
    I
    0.69
    п
    0.68
     films
    0.67
    Act Density 0.000%

    No Known Activations