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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oa
    -0.08
     Mexicans
    -0.07
    旅游局
    -0.07
     MMA
    -0.07
    LEM
    -0.07
    俗称
    -0.07
    iei
    -0.07
    sku
    -0.07
     ghetto
    -0.07
     venda
    -0.06
    POSITIVE LOGITS
    🌩
    0.07
     어�
    0.07
    пр
    0.07
    �
    0.07
    保護政策
    0.07
     câu
    0.06
    美德
    0.06
    properties
    0.06
    桩
    0.06
    脈
    0.06
    Act Density 0.062%

    No Known Activations