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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mellitus
    -0.09
     climate
    -0.08
    wealth
    -0.08
     sahib
    -0.08
     Boxer
    -0.08
     Adele
    -0.08
     aspiring
    -0.08
    طار
    -0.08
     Wealth
    -0.08
     Louise
    -0.08
    POSITIVE LOGITS
     helmet
    0.10
     helmets
    0.09
     Ordering
    0.09
     Helmet
    0.09
    Ordering
    0.09
     COLL
    0.09
     shaders
    0.09
    helmet
    0.09
    _ORDER
    0.09
     Haare
    0.09
    Act Density 0.003%

    No Known Activations