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

    Neuronpedia

    INDEX
    Explanations

    '''

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    輯
    -0.08
    옌
    -0.07
    过往
    -0.07
    健
    -0.07
     cree
    -0.07
     السيد
    -0.07
    ሕ
    -0.07
    ,event
    -0.07
    佰
    -0.07
    一级
    -0.06
    POSITIVE LOGITS
    城墙
    0.07
     medidas
    0.07
    歧视
    0.06
     �
    0.06
    我們
    0.06
     sum
    0.06
     liv
    0.06
    .server
    0.06
    ~":"
    0.06
     mask
    0.06
    Act Density 0.004%

    No Known Activations