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

    Neuronpedia

    INDEX
    Explanations

    existential risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reimburse
    0.97
    refund
    0.95
     patios
    0.94
     Patio
    0.91
     embossing
    0.91
     ادا
    0.90
    販売
    0.85
     Moistur
    0.84
    💁
    0.83
     patio
    0.83
    POSITIVE LOGITS
     apocalyptic
    2.00
     catastrophic
    1.64
     dystopian
    1.58
     apocalypse
    1.54
     prophecies
    1.52
     catastrophe
    1.52
     geopolitical
    1.49
     totalitarian
    1.49
     catastrophes
    1.47
     pessim
    1.43
    Act Density 0.115%

    No Known Activations