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

    Neuronpedia

    INDEX
    Explanations

    references to ideological conflicts and political struggles

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

    Ideologies (communism, fascism, liberal, conservative)

    np_acts-logits-general · gemini-2.0-flash

    political ideologies and affiliations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     librement
    -0.59
    ActivityResult
    -0.58
     humains
    -0.57
     Herodotus
    -0.56
     loisirs
    -0.56
     cittadino
    -0.55
     couverts
    -0.55
     spéciaux
    -0.55
     duele
    -0.55
     secondaires
    -0.55
    POSITIVE LOGITS
     conservative
    1.29
     liberal
    1.22
    conservative
    1.13
     anti
    1.04
     conservatism
    1.01
     conservatives
    1.00
    liberal
    0.97
     progres
    0.93
    conserv
    0.92
     liberalism
    0.92
    Act Density 0.626%

    No Known Activations