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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     какого
    0.58
    本身的
    0.57
     весьма
    0.56
     непосредственно
    0.56
     возникновения
    0.55
     strikingly
    0.55
     THAT
    0.54
     eigentlich
    0.54
     انتہائی
    0.54
     реально
    0.53
    POSITIVE LOGITS
     but
    0.88
     and
    0.87
     แต่
    0.67
    but
    0.65
     nhưng
    0.65
     এবং
    0.64
     If
    0.63
     그리고
    0.63
     while
    0.63
     While
    0.63
    Act Density 0.000%

    No Known Activations