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

    Neuronpedia

    INDEX
    Explanations

    references to research papers and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Location of information in books and articles

    np_acts-logits-general · gemini-2.0-flash

    page number references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.83
    -0.66
     '\\;'
    -0.64
     الرياضيه
    -0.61
    byr
    -0.60
     بيها
    -0.58
    Биография
    -0.56
     autorytatywna
    -0.54
     оригіналу
    -0.54
     continuant
    -0.53
    POSITIVE LOGITS
    DockStyle
    0.76
     xii
    0.68
     ix
    0.65
     xiv
    0.64
     xxiv
    0.62
     xix
    0.60
     viii
    0.59
     xxi
    0.58
     xvi
    0.58
     xiii
    0.57
    Act Density 0.292%

    No Known Activations