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

    Neuronpedia

    INDEX
    Explanations

    Race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .framework
    -0.07
     Vogue
    -0.07
    ==-
    -0.06
     Bugün
    -0.06
     тепер
    -0.06
    υχ
    -0.06
    게임
    -0.06
    addContainerGap
    -0.06
    boost
    -0.06
    ительных
    -0.06
    POSITIVE LOGITS
     Cust
    0.06
     pract
    0.06
    _crypto
    0.06
     Catalog
    0.06
    (util
    0.06
    _work
    0.06
    Dist
    0.06
     qualifies
    0.06
     imports
    0.06
    _components
    0.06
    Act Density 0.014%

    No Known Activations