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

    Neuronpedia

    INDEX
    Explanations

    strong adjectives that describe qualities or levels of experience and perception

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

    intensifiers and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.95
     Taktlose
    -0.82
     Normdatei
    -0.82
    nloa
    -0.81
    nodoc
    -0.81
     ब्रेकडाउन
    -0.77
    tagHelperRunner
    -0.76
    #+#
    -0.76
     שוליים
    -0.75
    :✨
    -0.75
    POSITIVE LOGITS
     and
    0.38
    ,
    0.34
    是一个
    0.29
     isa
    0.28
    作为一个
    0.28
     John
    0.28
     item
    0.28
     pretty
    0.27
     record
    0.27
     hard
    0.27
    Act Density 0.322%

    No Known Activations