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

    Neuronpedia

    INDEX
    Explanations

    expressions of interest, emotion, and social sentiment

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

    feelings and interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     independiente
    -0.37
     Administração
    -0.37
     autón
    -0.35
     intptr
    -0.34
     NSCoder
    -0.34
     Nacionales
    -0.33
     henne
    -0.33
    othesis
    -0.32
     roupa
    -0.32
     Ciências
    -0.32
    POSITIVE LOGITS
    parsedMessage
    0.73
    SharedCtor
    0.61
    webElementXpaths
    0.54
    rawDesc
    0.52
    tagHelperRunner
    0.52
     widespread
    0.50
     consternation
    0.50
    ➟
    0.50
    hyrchwyd
    0.50
     excitement
    0.48
    Act Density 0.091%

    No Known Activations