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

    Neuronpedia

    INDEX
    Explanations

    acquisition or acquiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    1.18
    مكن
    1.13
    كان
    1.10
    وسي
    1.09
    وري
    1.08
    اي
    1.06
    ек
    1.00
    اري
    1.00
    ра
    1.00
    一百
    0.97
    POSITIVE LOGITS
    p
    1.61
    ן
    1.58
     acquisition
    1.43
    ם
    1.43
     Acquisition
    1.41
    I
    1.38
    m
    1.32
    u
    1.29
    ro
    1.27
    ;
    1.27
    Act Density 0.006%

    No Known Activations