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

    Neuronpedia

    INDEX
    Explanations

    references to authority or strong opinions in conversations

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

    related to drafts or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reported
    -0.42
     zdroj
    -0.40
     coreano
    -0.40
     venezol
    -0.36
    reported
    -0.34
    paravant
    -0.34
     observed
    -0.34
     coreana
    -0.33
    据说
    -0.33
     sumber
    -0.33
    POSITIVE LOGITS
     EconPapers
    0.69
    KommentareTeilen
    0.69
     drafting
    0.66
    Marketing
    0.63
    Вот
    0.61
    ंदीखरीदारी
    0.61
     draft
    0.59
    WithIOException
    0.58
    draft
    0.58
    Draft
    0.57
    Act Density 0.013%

    No Known Activations