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

    Neuronpedia

    INDEX
    Explanations

    building on top of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.55
    ти
    1.45
    ট
    1.36
    在
    1.34
    asını
    1.34
    س
    1.34
    ங்கள்
    1.32
    де
    1.28
    υ
    1.28
    de
    1.27
    POSITIVE LOGITS
    THING
    1.88
    ни
    1.42
    E
    1.40
    습니다
    1.35
    am
    1.28
    ig
    1.28
    y
    1.25
    ara
    1.23
    িং
    1.21
     unscathed
    1.20
    Act Density 0.215%

    No Known Activations