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

    Neuronpedia

    INDEX
    Explanations

    data aggregation and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ని
    1.17
    し
    1.14
    ка
    1.13
     be
    1.00
    ır
    0.98
    abilir
    0.96
    ți
    0.95
    h
    0.95
    ك
    0.93
    ного
    0.91
    POSITIVE LOGITS
     aggregates
    1.26
    트
    1.22
     aggreg
    1.20
     aggregator
    1.16
    ال
    1.15
     aggregate
    1.14
     aggregated
    1.13
    ล
    1.07
     Aggregate
    1.01
     aggregation
    1.00
    Act Density 0.006%

    No Known Activations