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

    Neuronpedia

    INDEX
    Explanations

    gather information and assets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    se
    1.14
    ка
    1.13
     jeopard
    1.10
    v
    1.09
    sa
    1.05
    1
    1.05
    ك
    1.00
    ni
    0.96
    ä
    0.91
     ø
    0.90
    POSITIVE LOGITS
    ר
    1.57
     писа
    1.49
     powied
    1.46
     взя
    1.45
    er
    1.34
     rozpoczę
    1.33
    ა
    1.32
    ınız
    1.30
    ין
    1.29
    エース
    1.27
    Act Density 0.006%

    No Known Activations