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

    Neuronpedia

    INDEX
    Explanations

    numbers, quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    비를
    1.21
    비
    1.04
    beri
    1.03
     custos
    1.03
     prostat
    1.01
     diuretic
    1.00
     obligé
    1.00
     McCorm
    0.99
     diretta
    0.97
    jsr
    0.97
    POSITIVE LOGITS
     Ten
    1.33
    Ten
    1.32
    9
    1.21
     ten
    1.21
    8
    1.20
    TEN
    1.20
     Twelve
    1.20
     ۱۰
    1.18
    十
    1.17
     TEN
    1.17
    Act Density 0.735%

    No Known Activations