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

    Neuronpedia

    INDEX
    Explanations

    Slavic prefixes 'под'/'під'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    1.51
    a
    1.31
    AP
    1.21
     A
    1.18
    up
    1.16
    art
    1.15
    y
    1.14
    ia
    1.12
    ने
    1.10
    with
    1.10
    POSITIVE LOGITS
    大
    1.37
    ۵
    1.31
    ب
    1.29
    5
    1.28
    น
    1.27
    ↵
    1.25
    ۳
    1.24
    이었
    1.22
    습니다
    1.19
    人
    1.18
    Act Density 0.045%

    No Known Activations