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

    Neuronpedia

    INDEX
    Explanations

    price you, bananas you, periods you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    You
    0.49
     আপনাকে
    0.43
     You
    0.39
     คุณ
    0.38
     Вас
    0.38
     morate
    0.37
     ćete
    0.36
    给她
    0.36
    னால்
    0.36
    them
    0.36
    POSITIVE LOGITS
     they
    0.88
     которую
    0.74
     koju
    0.70
     she
    0.67
    ที่คุณ
    0.67
    ที่เรา
    0.64
     we
    0.62
     that
    0.61
     he
    0.60
     theyre
    0.60
    Act Density 0.179%

    No Known Activations