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

    Neuronpedia

    INDEX
    Explanations

    references to political affiliations and social issues related to conservatism and identity politics

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

    Adjectives describing groups of people

    np_acts-logits-general · gemini-2.0-flash

    types of people and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vœux
    -0.88
     démocr
    -0.74
     vectorielles
    -0.69
     financières
    -0.68
     définiti
    -0.66
     gouvernements
    -0.64
     aveug
    -0.64
     églises
    -0.62
     écrits
    -0.62
     sanitarias
    -0.61
    POSITIVE LOGITS
     souls
    0.88
     beings
    0.81
     folk
    0.77
     individuals
    0.74
    lossians
    0.70
     natives
    0.68
    GEBURTSDATUM
    0.68
     dwellers
    0.67
     Americans
    0.67
     humans
    0.67
    Act Density 0.697%

    No Known Activations