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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sailed
    -0.08
     važ
    -0.08
    (stack
    -0.08
     luxuri
    -0.08
    อย
    -0.08
     schön
    -0.08
    (adj
    -0.08
     nestled
    -0.08
     marketers
    -0.08
     überrascht
    -0.08
    POSITIVE LOGITS
    规定
    0.11
    privacy
    0.09
    security
    0.09
     חוק
    0.09
     سياسة
    0.09
     privacy
    0.09
     Privacy
    0.09
     സുരക്ഷ
    0.09
     censorship
    0.08
     ആവശ്യ
    0.08
    Act Density 0.003%

    No Known Activations