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

    Neuronpedia

    INDEX
    Explanations

    SEO is Crucial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⵅ
    0.49
    우스
    0.48
    મેન્ટ
    0.47
     setIs
    0.47
    푦
    0.47
     değişiklik
    0.46
    벳
    0.45
    testAvg
    0.45
    ಾಪ
    0.45
    你说
    0.45
    POSITIVE LOGITS
     -,
    0.49
     Jensen
    0.49
    he
    0.47
     (
    0.47
     Pavlov
    0.46
     ,
    0.45
    -,
    0.43
     Mandarin
    0.43
    (
    0.42
    at
    0.41
    Act Density 0.003%

    No Known Activations