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

    Neuronpedia

    INDEX
    Explanations

    Rate/CRO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Notification
    -0.09
    天津
    -0.08
    .Qu
    -0.08
     broadcasts
    -0.08
    .Groups
    -0.08
    记者
    -0.08
    .Schedule
    -0.08
    laşı
    -0.08
     খবর
    -0.07
    .bluetooth
    -0.07
    POSITIVE LOGITS
     सुधार
    0.13
     સુધ
    0.12
     improvements
    0.12
     améliorer
    0.12
     개선
    0.12
     izbol
    0.12
    改善
    0.12
    优化
    0.12
     Improve
    0.11
     تحسين
    0.11
    Act Density 0.009%

    No Known Activations