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

    Neuronpedia

    INDEX
    Explanations

    file downloads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ixin
    -0.08
    ron
    -0.08
    introduced
    -0.08
     ruling
    -0.08
    flammation
    -0.08
     improvis
    -0.08
     dept
    -0.08
    _fs
    -0.08
     objections
    -0.08
     Spurs
    -0.07
    POSITIVE LOGITS
    下载安装
    0.11
    /download
    0.10
    .download
    0.10
    (download
    0.10
     télécharger
    0.10
    下載
    0.10
     डाउनलोड
    0.09
    .Download
    0.09
     다운로드
    0.09
    下载
    0.09
    Act Density 0.078%

    No Known Activations