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

    Neuronpedia

    INDEX
    Explanations

    references to books, publications, and written materials

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

    books and publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ffine
    -0.47
    LabelTagHelper
    -0.43
     상세
    -0.42
     partida
    -0.42
    raktion
    -0.41
    TRAILING
    -0.40
     AliExpress
    -0.40
    цезда
    -0.39
    这条
    -0.39
    GOTREF
    -0.39
    POSITIVE LOGITS
     book
    0.78
     booklet
    0.77
     handbook
    0.68
    book
    0.68
     books
    0.67
     workbook
    0.67
     booklets
    0.66
     betweenstory
    0.62
     manuals
    0.57
     Book
    0.57
    Act Density 0.031%

    No Known Activations