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

    Neuronpedia

    INDEX
    Explanations

    code examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     establish
    0.67
     settings
    0.67
     অবহিত
    0.66
     sign
    0.65
     Framework
    0.64
     Kickstarter
    0.64
     jump
    0.63
     Establish
    0.62
     estoppel
    0.62
     SCRE
    0.61
    POSITIVE LOGITS
    ```
    1.14
    Example
    1.04
    example
    0.95
     Example
    0.94
    例子
    0.93
    示例
    0.88
    пример
    0.87
    Examples
    0.86
     Пример
    0.85
    例
    0.85
    Act Density 0.233%

    No Known Activations