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

    Neuronpedia

    INDEX
    Explanations

    wiki formatting and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barbe
    -0.09
    .rabbit
    -0.08
    екте
    -0.08
    متع
    -0.08
    quite
    -0.08
     लंबे
    -0.08
     लोगों
    -0.07
    );*/↵
    -0.07
     מאוד
    -0.07
    (stack
    -0.07
    POSITIVE LOGITS
     скачать
    0.09
    ︎
    0.09
     link
    0.09
     Link
    0.09
    ←
    0.09
     hyperlink
    0.08
     ссылка
    0.08
    链接
    0.08
     링크
    0.08
     ←
    0.08
    Act Density 0.075%

    No Known Activations