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

    Neuronpedia

    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BuilderInterface
    -0.07
     während
    -0.07
    [from
    -0.07
     השונים
    -0.07
     overloaded
    -0.07
    ∥
    -0.07
     Toledo
    -0.07
    作风建设
    -0.07
    抢抓
    -0.07
     abuses
    -0.07
    POSITIVE LOGITS
     Sub
    0.08
    DataContext
    0.07
    лок
    0.07
    market
    0.07
    óc
    0.07
    PRODUCT
    0.07
    ńst
    0.07
    컬
    0.07
    弈
    0.06
    ưng
    0.06
    Act Density 0.012%

    No Known Activations