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

    Neuronpedia

    INDEX
    Explanations

    grouping or arrangement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    1.66
    se
    1.35
     be
    1.27
    ك
    1.17
     an
    1.15
    <0x80>
    1.09
    ные
    1.05
    sp
    1.04
    ,
    1.04
    ian
    1.03
    POSITIVE LOGITS
    トップ
    1.41
    র
    1.36
    트
    1.32
    ין
    1.27
     agrup
    1.22
    Ди
    1.21
    Ак
    1.21
    자
    1.21
    Тех
    1.20
    Кла
    1.19
    Act Density 0.027%

    No Known Activations