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

    Neuronpedia

    INDEX
    Explanations

    terms related to options, candidates, and choices in various contexts

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

    possibilities and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HttpHeaders
    -0.32
     stage
    -0.31
    /-/
    -0.30
    TagMode
    -0.29
     end
    -0.28
    Gesellschaft
    -0.26
     etapa
    -0.26
    throw
    -0.26
     and
    -0.25
    /
    -0.25
    POSITIVE LOGITS
    rungsseite
    0.81
     autorytatywna
    0.77
     مشين
    0.77
    NameInMap
    0.75
     المعيارى
    0.73
     nahilalakip
    0.68
     mergeFrom
    0.68
    findpost
    0.68
    reportWebVitals
    0.66
    BufferException
    0.65
    Act Density 0.070%

    No Known Activations