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

    Neuronpedia

    INDEX
    Explanations

    and agreeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    க
    0.45
    습니다
    0.44
     sitios
    0.43
    𒌆
    0.43
     conceitos
    0.43
    는다
    0.43
    ک
    0.42
    ಯ
    0.41
    茄
    0.41
    此
    0.40
    POSITIVE LOGITS
    ed
    0.64
    al
    0.57
    h
    0.51
    ek
    0.50
    و
    0.48
    re
    0.43
    am
    0.43
    an
    0.43
    pl
    0.42
     For
    0.42
    Act Density 0.000%

    No Known Activations