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

    Neuronpedia

    INDEX
    Explanations

    to insert recursive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sz
    0.48
     zapewn
    0.47
    ை
    0.46
    shore
    0.45
    کن
    0.45
    шкин
    0.45
    te
    0.44
    wa
    0.44
    heng
    0.44
    tx
    0.44
    POSITIVE LOGITS
    儩
    0.42
     утро
    0.42
     Oaks
    0.41
    原材料
    0.41
    到
    0.41
     便
    0.41
    이란
    0.40
    انات
    0.39
     हजारों
    0.39
     검색
    0.39
    Act Density 0.072%

    No Known Activations