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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical conflicts and interventions involving the U.S. and Russia

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

    Russia and Russians

    np_acts-logits-general · gemini-2.0-flash

    Russian interference, crime, and politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brabant
    -0.64
     Brind
    -0.61
    TagMode
    -0.61
     تضيفلها
    -0.61
    AsUp
    -0.59
    addCriterion
    -0.58
     Bonita
    -0.56
    Honduras
    -0.55
    出版年
    -0.55
    각주
    -0.55
    POSITIVE LOGITS
     Russian
    1.81
     Russia
    1.69
    Russian
    1.56
    Russia
    1.49
     Russians
    1.41
     Rusia
    1.38
     Moscow
    1.38
     Putin
    1.38
     RUSS
    1.37
     russian
    1.36
    Act Density 0.306%

    No Known Activations