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

    Neuronpedia

    INDEX
    Explanations

    raising the driving age

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indentLevel
    0.22
    ショナル
    0.22
    дын
    0.21
    ዐይን
    0.20
    неоп
    0.20
     ಒಳಗ
    0.20
     leverages
    0.20
    ಂಡ್
    0.20
    ㄎ
    0.20
    퇸
    0.20
    POSITIVE LOGITS
     […]
    0.23
     [...]
    0.21
     (...)
    0.19
     Unable
    0.19
    ...
    0.19
    ...,
    0.19
    ....
    0.18
    pdf
    0.18
    ```
    0.18
     hardly
    0.17
    Act Density 0.422%

    No Known Activations