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

    Neuronpedia

    INDEX
    Explanations

    security, scarcity, and governance of resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gerät
    0.84
     lunatic
    0.77
     thrill
    0.77
     receptionist
    0.74
     işlem
    0.73
     disgust
    0.73
     columnas
    0.72
     kontakt
    0.72
    違反
    0.71
     fooling
    0.70
    POSITIVE LOGITS
     security
    1.20
     governance
    1.13
     policies
    1.07
     policy
    1.05
     policym
    1.05
     sustainability
    1.04
     Security
    1.03
     shortages
    1.01
    security
    1.00
    Security
    0.99
    Act Density 0.131%

    No Known Activations