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

    Neuronpedia

    INDEX
    Explanations

    anthropocentric and anthropomorphic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cinética
    0.71
    BeerItem
    0.65
    bellum
    0.65
    部的
    0.62
     علامت
    0.62
    allowSlide
    0.61
     quảng
    0.61
     phonetic
    0.61
     buoyant
    0.60
     alkenyl
    0.59
    POSITIVE LOGITS
     WORLD
    1.06
    WORLD
    1.04
     relationships
    1.04
     world
    1.03
     assumptions
    1.02
     problems
    1.00
     World
    1.00
    世界
    0.99
    World
    0.98
     problem
    0.97
    Act Density 0.000%

    No Known Activations