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

    Neuronpedia

    INDEX
    Explanations

    total followed by quantity or calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.52
    ку
    1.46
    ка
    1.45
    ни
    1.16
    هم
    1.15
    ,
    1.14
    ی
    1.01
    ల
    1.01
    ون
    1.00
    ία
    1.00
    POSITIVE LOGITS
    at
    1.26
    u
    1.23
     Total
    1.17
    m
    1.13
     totale
    0.96
    as
    0.96
    ล
    0.95
    .
    0.94
    to
    0.93
    total
    0.93
    Act Density 0.037%

    No Known Activations