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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experience and subjective opinions

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

    common words

    np_acts-logits-general · gemini-2.0-flash

    defining state or characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -------------</
    -0.35
     مدن
    -0.31
    дента
    -0.27
    透露
    -0.26
     Wig
    -0.25
    care
    -0.25
    spielen
    -0.25
    couverture
    -0.25
    cara
    -0.24
     beam
    -0.24
    POSITIVE LOGITS
     CallOverrides
    0.71
     برانيه
    0.71
     esternos
    0.69
    LookAnd
    0.64
    EDEFAULT
    0.62
     EconPapers
    0.61
    ardless
    0.59
     שוליים
    0.58
    MessageTagHelper
    0.57
    ValueStyle
    0.56
    Act Density 0.358%

    No Known Activations