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

    Neuronpedia

    INDEX
    Explanations

    lists of descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gemüse
    0.64
     sorghum
    0.64
     aliphatic
    0.60
    oteurs
    0.59
     Drinfeld
    0.59
     Lobkovic
    0.58
     arXiv
    0.58
     pyridine
    0.58
     Eurostile
    0.57
     deuteron
    0.55
    POSITIVE LOGITS
    所謂
    0.63
    涉及到
    0.63
    obviously
    0.59
    ictionary
    0.58
    典型的
    0.58
    rightarrow
    0.57
    Answer
    0.57
    ൊരു
    0.57
    所谓的
    0.56
    டுவது
    0.56
    Act Density 2.733%

    No Known Activations