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

    Neuronpedia

    INDEX
    Explanations

    so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    1.87
    न
    1.30
    m
    1.28
    امة
    1.20
    um
    1.17
    가의
    1.16
    ка
    1.13
    st
    1.12
    mountain
    1.11
    s
    1.10
    POSITIVE LOGITS
    othed
    2.29
    journ
    2.15
    oooo
    2.04
     sánh
    2.03
    ledad
    1.98
    jour
    1.92
    oner
    1.91
     ώστε
    1.90
    oooooooo
    1.84
    aking
    1.83
    Act Density 0.042%

    No Known Activations