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

    Neuronpedia

    INDEX
    Explanations

    references to the number of people involved in various contexts

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

    people died or were killed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndroidJUnit
    -0.47
     tradição
    -0.46
     &___
    -0.46
    StandardCharsets
    -0.45
     matéria
    -0.45
    SourceChecksum
    -0.44
     optimizar
    -0.43
     ModelExpression
    -0.43
    ampingi
    -0.43
     prácti
    -0.43
    POSITIVE LOGITS
    People
    0.80
     People
    0.79
     PEOPLE
    0.72
    people
    0.71
    PEOPLE
    0.70
     people
    0.70
     person
    0.68
    someone
    0.68
    Someone
    0.67
    Person
    0.66
    Act Density 0.017%

    No Known Activations