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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpected reactions

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

    associated with surprise or shock

    np_acts-logits-general · gemini-2.0-flash

    shocked surprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.48
    WebElementEntity
    -0.47
     Pro
    -0.46
     تانيه
    -0.44
     Verfügung
    -0.43
     igény
    -0.43
    حياتها
    -0.43
     useHistory
    -0.42
    Pro
    -0.42
    pageY
    -0.41
    POSITIVE LOGITS
     shocked
    1.71
     astonished
    1.53
     surprised
    1.52
     astonishment
    1.48
     stunned
    1.47
     shock
    1.43
     startled
    1.42
    shocked
    1.40
     surprise
    1.37
    surprised
    1.30
    Act Density 0.236%

    No Known Activations