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

    Neuronpedia

    INDEX
    Explanations

    references to political entities and their power dynamics

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

    nations and powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.47
    XtraReports
    -0.44
    Vidite
    -0.44
    grunns
    -0.44
     împre
    -0.41
    цездатний
    -0.41
    horizontalLayout
    -0.40
    ăzi
    -0.40
    verture
    -0.40
    RenderAtEndOf
    -0.40
    POSITIVE LOGITS
     countries
    0.57
     Countries
    0.53
     nations
    0.53
     nation
    0.50
    TestingModule
    0.49
     naciones
    0.48
     Nation
    0.45
    ConstraintMaker
    0.45
    countries
    0.44
    MigrationBuilder
    0.44
    Act Density 0.023%

    No Known Activations