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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or contentment

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

    expressions of happiness or positive sentiment related to assisting others

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

    happy to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.84
    sidemargin
    -0.78
     pinulongan
    -0.64
    urlpatterns
    -0.62
    NewUrlParser
    -0.61
     resourceCulture
    -0.60
    ImageContext
    -0.59
     Italijanski
    -0.58
    Portály
    -0.58
    PMailer
    -0.58
    POSITIVE LOGITS
     oblige
    0.57
    etsu
    0.55
     Glad
    0.55
     aidant
    0.53
    Reports
    0.50
     Stunde
    0.50
     GLAD
    0.49
    ences
    0.48
     }}"></
    0.48
     reports
    0.48
    Act Density 0.017%

    No Known Activations