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

    Neuronpedia

    INDEX
    Explanations

    Dataset loading (code)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creditor
    -0.09
    集团
    -0.08
     skyscr
    -0.08
     intense
    -0.08
     främ
    -0.08
     abrasive
    -0.08
     twenties
    -0.08
     heightened
    -0.08
     magnesium
    -0.08
     customer
    -0.07
    POSITIVE LOGITS
    下载
    0.14
     डाउनलोड
    0.14
     下载
    0.14
     다운로드
    0.14
    .download
    0.13
     Download
    0.13
    Download
    0.13
    _download
    0.13
    下載
    0.13
    .Download
    0.12
    Act Density 0.006%

    No Known Activations