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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their associated actions or events

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

    Names followed by "and"

    np_acts-logits-general · gemini-2.0-flash

    names like Michael, Mark, James, Smith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.68
     EconPapers
    -0.64
    transQ
    -0.56
     AssemblyCulture
    -0.56
     ProtoMessage
    -0.54
    StructEnd
    -0.53
     ujednoznacz
    -0.50
     disambiguazione
    -0.50
     HasFactory
    -0.49
    KommentareTeilen
    -0.48
    POSITIVE LOGITS
     finally
    0.38
     prefers
    0.38
     and
    0.36
     paramString
    0.36
    Finalmente
    0.35
    rboles
    0.35
    >');
    0.34
    참고
    0.34
    '");
    0.34
     bravely
    0.34
    Act Density 0.267%

    No Known Activations