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

    Neuronpedia

    INDEX
    Explanations

    UI code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boul
    0.45
    nione
    0.45
    ),
    0.45
    ",
    0.44
     ...
    0.42
     historic
    0.41
     Partial
    0.41
     ช่อง
    0.41
     FROM
    0.41
     {
    0.40
    POSITIVE LOGITS
     odmah
    0.45
    你就
    0.43
    立即
    0.42
    しまう
    0.41
    اس
    0.41
    شاه
    0.40
    掉
    0.40
    klich
    0.39
    스팅
    0.39
     तत्काल
    0.39
    Act Density 0.003%

    No Known Activations