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

    Neuronpedia

    INDEX
    Explanations

    references to ideals and principles in a political context

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

    ideals and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.63
     Maladies
    -0.53
     granny
    -0.52
     trouser
    -0.52
    momix
    -0.49
     trousers
    -0.49
    contentLoaded
    -0.48
     sinu
    -0.47
     électronique
    -0.47
     Espagne
    -0.47
    POSITIVE LOGITS
     ideals
    1.34
     idealism
    1.07
     idealistic
    1.02
     ideal
    1.01
    Ideal
    0.97
     Ideal
    0.96
     IDEAL
    0.95
     ideales
    0.91
    ideal
    0.90
    理想
    0.84
    Act Density 0.009%

    No Known Activations