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

    Neuronpedia

    INDEX
    Explanations

    following instructions thoughtfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lineColorSpace
    0.61
    ░
    0.43
    なら
    0.42
     ين
    0.42
     filha
    0.40
    ้า
    0.38
    ذي
    0.38
     feiern
    0.38
    ллер
    0.38
     زیرا
    0.38
    POSITIVE LOGITS
    mouseup
    0.41
    aston
    0.40
    hspace
    0.40
    𝗛
    0.39
    ＜
    0.39
    Tooltip
    0.39
     (!$
    0.38
    成都
    0.38
     হচ্ছে
    0.38
    প্রতি
    0.38
    Act Density 0.088%

    No Known Activations