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

    Neuronpedia

    INDEX
    Explanations

    placing bets on outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    া
    0.97
    ه
    0.81
    اً
    0.73
    ς
    0.73
    ی
    0.71
    ется
    0.67
    ا
    0.64
    ה
    0.63
    ের
    0.62
    TabBar
    0.62
    POSITIVE LOGITS
    to
    0.83
    is
    0.73
     bets
    0.71
    EN
    0.67
    kan
    0.67
     això
    0.66
    shire
    0.64
    el
    0.61
     and
    0.60
    cm
    0.59
    Act Density 0.002%

    No Known Activations