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

    Neuronpedia

    INDEX
    Explanations

    write a specific output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yourself
    0.50
    your
    0.49
     вашем
    0.48
    ujete
    0.46
     yourselves
    0.45
     yourself
    0.45
    あなたの
    0.43
    يدك
    0.43
    你的
    0.42
     ваш
    0.41
    POSITIVE LOGITS
     me
    0.61
     мне
    0.59
     us
    0.52
     meille
    0.51
     nám
    0.47
     нам
    0.47
     нами
    0.44
     нас
    0.44
     ہمیں
    0.43
     μου
    0.42
    Act Density 0.001%

    No Known Activations