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

    Neuronpedia

    INDEX
    Explanations

    Let

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     us
    0.61
     нами
    0.60
     siguiendo
    0.55
     pusher
    0.55
     sugi
    0.53
     علينا
    0.52
     нас
    0.52
     ہمیں
    0.52
     vadanti
    0.52
     nám
    0.51
    POSITIVE LOGITS
     know
    1.05
    know
    0.97
    知道
    0.88
    known
    0.84
    知
    0.83
    Known
    0.80
     known
    0.80
     knows
    0.79
     Know
    0.78
    Know
    0.76
    Act Density 0.029%

    No Known Activations