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

    Neuronpedia

    INDEX
    Explanations

    parenthetical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.75
     as
    0.74
    4
    0.73
     is
    0.70
     be
    0.67
    3
    0.65
     of
    0.65
    ),
    0.63
    5
    0.62
    ።
    0.62
    POSITIVE LOGITS
    و
    0.72
    おそらく
    0.61
    น
    0.60
    और
    0.58
    同じ
    0.58
    기와
    0.57
    스와
    0.57
    その
    0.55
    스가
    0.54
    이니
    0.54
    Act Density 0.345%

    No Known Activations