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

    Neuronpedia

    INDEX
    Explanations

    references to violent incidents involving law enforcement and their justifications

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

    justified deadly force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.45
    Dimensiones
    -0.39
     Jurí
    -0.39
     pasión
    -0.38
     entanto
    -0.38
    chenkt
    -0.37
     promociones
    -0.37
     StatelessWidget
    -0.37
     paixão
    -0.36
    humidité
    -0.36
    POSITIVE LOGITS
    WebElementEntity
    0.65
    VYMaps
    0.55
    Personensuche
    0.49
    webElementXpaths
    0.49
     BoxFit
    0.47
     Autorizaciones
    0.46
    GEBURTSDATUM
    0.45
     MainAxisSize
    0.44
     pinulongan
    0.44
    Autoritní
    0.43
    Act Density 0.006%

    No Known Activations