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

    Neuronpedia

    INDEX
    Explanations

    numerical references or data points

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

    Numbers within square brackets

    np_acts-logits-general · gemini-2.0-flash

    citation numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.66
     ModelExpression
    -0.58
    (!__
    -0.51
    IsContent
    -0.50
    WriteTagHelper
    -0.47
     تانيه
    -0.45
     komende
    -0.42
    AndEndTag
    -0.41
     wikipagina
    -0.40
    tagHelper
    -0.38
    POSITIVE LOGITS
    zzleHttp
    0.51
    ViewFeatures
    0.45
     fevere
    0.44
     indisponible
    0.43
     milla
    0.43
    uurs
    0.42
    Disliked
    0.42
     Escolar
    0.42
    AISSEE
    0.42
     Gén
    0.42
    Act Density 0.100%

    No Known Activations