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

    Neuronpedia

    INDEX
    Explanations

    expressions of positivity and high-quality experiences

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

    Follows "great" or "nice" and relates to positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    highly positive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.59
    buttonBar
    -0.59
    ajur
    -0.53
    それでも
    -0.53
    rans
    -0.51
    jupiter
    -0.50
    mars
    -0.49
    ViewChild
    -0.49
     nhiễm
    -0.48
    서는
    -0.48
    POSITIVE LOGITS
    पया
    0.76
    ValueStyle
    0.75
     EconPapers
    0.72
     disambiguazione
    0.71
     nice
    0.67
    зулта
    0.65
     sekali
    0.63
    clearfix
    0.63
    NameInMap
    0.62
    anskje
    0.61
    Act Density 0.122%

    No Known Activations