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

    Neuronpedia

    INDEX
    Explanations

    AI's impact on humanity's future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     круг
    0.72
    aktur
    0.72
    uliers
    0.71
    न्दर
    0.71
    asionally
    0.70
    деб
    0.70
    ullie
    0.70
    invoice
    0.70
    Borrow
    0.69
     fillets
    0.69
    POSITIVE LOGITS
     totalitarian
    1.68
     dystopian
    1.64
     utopian
    1.49
     dyst
    1.44
     Utopia
    1.42
     civilizations
    1.42
     civilization
    1.40
     global
    1.30
     societies
    1.28
     humanity
    1.28
    Act Density 0.349%

    No Known Activations