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

    Neuronpedia

    INDEX
    Explanations

    AI pronouns me and I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    だが
    0.47
    ness
    0.42
    utter
    0.42
    bs
    0.41
    span
    0.41
     aber
    0.40
    lessness
    0.40
    uler
    0.40
    那個
    0.40
    stroke
    0.39
    POSITIVE LOGITS
     আমাকে
    1.30
     me
    1.22
     mnie
    1.20
    我
    1.18
     मुझे
    1.13
     мне
    1.13
     நான்
    1.09
     моих
    1.09
    我的
    1.09
     আমার
    1.06
    Act Density 0.223%

    No Known Activations