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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pihaknya
    1.29
     nende
    0.87
    让他们
    0.85
     deras
    0.83
     mereka
    0.83
     deres
    0.82
     ними
    0.79
     их
    0.75
    миз
    0.72
    newswire
    0.72
    POSITIVE LOGITS
     you
    5.76
    you
    5.25
     você
    4.91
    You
    4.90
     bạn
    4.81
    你
    4.75
     your
    4.74
     You
    4.70
    your
    4.48
     вас
    4.47
    Act Density 5.731%

    No Known Activations