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

    Neuronpedia

    INDEX
    Explanations

    newness, updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    670
    -0.07
    .medium
    -0.07
    Fully
    -0.06
     overcome
    -0.06
    ilyn
    -0.06
    默
    -0.06
     illuminated
    -0.06
     officially
    -0.06
    小学
    -0.06
     tối
    -0.06
    POSITIVE LOGITS
     freshness
    0.08
     FactoryBot
    0.08
    .mo
    0.07
     svě
    0.07
     ذه
    0.06
     distinctions
    0.06
    **
↵
    0.06
     Scrap
    0.06
    transform
    0.06
    IndexOf
    0.06
    Act Density 0.013%

    No Known Activations