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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alterations
    -0.08
    陆军
    -0.07
     imageName
    -0.07
     bathing
    -0.07
    Customers
    -0.07
     peny
    -0.07
     PART
    -0.06
    .HasKey
    -0.06
    小于
    -0.06
    ﲤ
    -0.06
    POSITIVE LOGITS
     Dispatch
    0.07
    'o
    0.07
    _reduce
    0.06
    controller
    0.06
    Chicago
    0.06
    Tiny
    0.06
    iki
    0.06
    ⁺
    0.06
    kil
    0.06
    uto
    0.06
    Act Density 0.027%

    No Known Activations