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

    Neuronpedia

    INDEX
    Explanations

    programming annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    grimas
    2.65
    ть
    2.57
     πάν
    2.51
    ться
    2.47
    ढ
    2.46
    ample
    2.44
    ियम
    2.42
    ४
    2.40
    of
    2.40
     चलकर
    2.37
    POSITIVE LOGITS
    даги
    3.03
    ي
    2.89
    да
    2.84
    िनी
    2.82
    st
    2.80
    至于
    2.72
    رسی
    2.72
    စိတ်အပိုင်း
    2.64
    સ
    2.63
    ف
    2.62
    Act Density 0.003%

    No Known Activations