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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong feelings or significant actions

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

    Comes before words of emphasis ("really," "truly")

    np_acts-logits-general · gemini-2.0-flash

    the intensifier "really"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.56
    PDE
    -0.46
    ViewImports
    -0.46
    UnitTesting
    -0.46
     kaarangay
    -0.44
    ContentLoaded
    -0.43
    enumi
    -0.43
    MINI
    -0.43
     EDP
    -0.42
    SLP
    -0.42
    POSITIVE LOGITS
     really
    0.96
     Really
    0.88
    really
    0.88
    Really
    0.85
     realmente
    0.84
     REALLY
    0.81
     virkelig
    0.75
     vraiment
    0.75
     verkligen
    0.70
     truly
    0.69
    Act Density 0.263%

    No Known Activations