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

    Neuronpedia

    INDEX
    Explanations

    social class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    真人
    -0.08
     Rennen
    -0.08
    Dice
    -0.08
    .ACTION
    -0.08
     तरीके
    -0.07
     resep
    -0.07
     قوانین
    -0.07
    보고
    -0.07
     receta
    -0.07
     presets
    -0.07
    POSITIVE LOGITS
     elites
    0.14
     elite
    0.10
     populace
    0.10
     জনগ
    0.10
     населения
    0.10
    층
    0.10
     psyche
    0.10
    阶
    0.10
     المجتمع
    0.09
     clergy
    0.09
    Act Density 0.032%

    No Known Activations