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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     المختلفة
    0.63
     অনেকে
    0.60
     nhưng
    0.58
     ngunit
    0.57
     แต่
    0.55
    但也
    0.55
     אבל
    0.53
     lakini
    0.53
     लेकिन
    0.51
     البعض
    0.50
    POSITIVE LOGITS
     the
    0.66
     সেই
    0.55
     that
    0.52
     exactly
    0.50
    the
    0.49
    uradaki
    0.47
     nicknamed
    0.46
    {\
    0.46
     of
    0.46
    那位
    0.46
    Act Density 1.207%

    No Known Activations