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

    Neuronpedia

    INDEX
    Explanations

    direct address / second person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     제가
    1.37
     저희
    1.33
    您
    1.32
    您的
    1.27
     저는
    1.22
     আপনাদের
    1.17
     saya
    1.16
     您
    1.16
    如果您
    1.15
     vostro
    1.14
    POSITIVE LOGITS
     тебе
    2.80
     тебя
    2.66
     тво
    2.55
     тобі
    2.36
     тобой
    2.25
     তোমার
    2.20
     তোমাকে
    2.17
     puedes
    2.16
     możesz
    2.14
     σου
    2.14
    Act Density 0.136%

    No Known Activations