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
     academics
    -0.06
    inv
    -0.06
     комплекс
    -0.06
     research
    -0.06
    ㇰ
    -0.06
    比较多
    -0.06
    ```
    -0.06
    ซ
    -0.06
    覆
    -0.06
    进行了
    -0.06
    POSITIVE LOGITS
    сыл
    0.08
    -scroll
    0.08
     kosher
    0.07
     حت
    0.07
    /Common
    0.07
    翡
    0.07
    .OPEN
    0.07
     dto
    0.07
    �
    0.07
    _SF
    0.07
    Act Density 0.006%

    No Known Activations