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

    Neuronpedia

    INDEX
    Explanations

    concepts related to public perception and societal judgment

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

    people talking about others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.58
    WebElementEntity
    -0.52
    GEBURTSDATUM
    -0.52
     محفوظة
    -0.51
     EconPapers
    -0.50
     ब्रेकडाउन
    -0.48
    Chham
    -0.44
    GIH
    -0.43
     propOrder
    -0.42
    StackNavigator
    -0.42
    POSITIVE LOGITS
     gossi
    0.55
     AppCompatTheme
    0.53
     whispers
    0.47
     gossip
    0.45
     crowds
    0.45
     whispered
    0.44
    蜚
    0.43
     wier
    0.43
    外界
    0.41
     whispering
    0.41
    Act Density 0.197%

    No Known Activations