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

    Neuronpedia

    INDEX
    Explanations

    specific terms and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشتمل
    0.42
     څرنګ
    0.40
    lewati
    0.39
    ჷ
    0.39
     جوړونکی
    0.39
     изда
    0.39
    প্তাহ
    0.39
     gasoline
    0.38
    responsive
    0.38
     وړاند
    0.38
    POSITIVE LOGITS
    ad
    0.49
     Margin
    0.44
    ag
    0.44
    oleic
    0.43
    ua
    0.42
    Margins
    0.42
    洮
    0.42
     Bete
    0.41
     Fail
    0.41
     Ad
    0.40
    Act Density 0.000%

    No Known Activations