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

    Neuronpedia

    INDEX
    Explanations

    searchendmovieredmixed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്ക്‌
    0.43
     laatste
    0.42
     έως
    0.42
    と思いますが
    0.41
     bakın
    0.41
    TreeWidgetItem
    0.40
    癸
    0.40
    파일
    0.40
    ﻪ
    0.39
     keselamatan
    0.38
    POSITIVE LOGITS
    ar
    0.49
     insides
    0.47
    ut
    0.46
    ides
    0.46
    pont
    0.46
    ila
    0.45
    ichi
    0.45
    ights
    0.44
    vian
    0.44
     sermons
    0.44
    Act Density 3.017%

    No Known Activations