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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to filtering options or settings

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

    faceted filtering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.59
    arraycopy
    -0.50
    AppMethodBeat
    -0.49
     ***!
    -0.49
    awaiter
    -0.47
    LogFactory
    -0.47
    rawDesc
    -0.46
     AssemblyVersion
    -0.46
    GenerationType
    -0.46
    BASEPATH
    -0.45
    POSITIVE LOGITS
     filter
    0.51
     Filter
    0.48
     filters
    0.47
    filterBy
    0.45
     Filters
    0.42
    Filters
    0.41
    filters
    0.40
    LEncoder
    0.40
    filter
    0.39
     filtros
    0.39
    Act Density 0.010%

    No Known Activations