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

    Neuronpedia

    INDEX
    Explanations

    summary/report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cascade
    -0.08
     �
    -0.08
     underserved
    -0.08
     Hollywood
    -0.08
     crossorigin
    -0.08
     celebrities
    -0.08
     Links
    -0.08
     Laugh
    -0.08
     catalytic
    -0.08
     marketed
    -0.08
    POSITIVE LOGITS
    报告
    0.14
    成绩
    0.12
     제출
    0.11
    提交
    0.11
    Report
    0.11
     laporan
    0.11
    正文
    0.11
    .report
    0.11
     report
    0.11
    .Report
    0.11
    Act Density 0.043%

    No Known Activations