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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to self or AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    迠
    0.52
    बाट
    0.52
     dina
    0.51
    ній
    0.47
     při
    0.47
    从
    0.44
     renew
    0.43
    ntag
    0.43
    /');
    0.43
    ম্মদ
    0.42
    POSITIVE LOGITS
     🙂
    0.76
     :)
    0.67
     and
    0.66
     మరియు
    0.62
     😉
    0.61
    )
    0.61
     Nhưng
    0.60
     ContentValues
    0.59
    !.
    0.58
     :/
    0.58
    Act Density 0.022%

    No Known Activations