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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions that convey positive qualities or commendations

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

    positive sentiment after "was"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.52
     preventiva
    -0.51
     básicos
    -0.47
     potenciales
    -0.44
     gráfico
    -0.41
     noDo
    -0.41
     básicas
    -0.41
     recours
    -0.41
     preventivo
    -0.41
     disambiguazione
    -0.40
    POSITIVE LOGITS
    ftagPool
    0.63
     MainAxisSize
    0.44
    󠁣
    0.44
    Życiorys
    0.44
    setupUi
    0.43
    boneca
    0.42
    bootstrapcdn
    0.42
     సౌకర్య
    0.42
     delightful
    0.40
    omena
    0.40
    Act Density 0.016%

    No Known Activations