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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Creating
    -0.08
     veta
    -0.08
     Introducing
    -0.07
    ật
    -0.07
     alfa
    -0.07
     filmmaking
    -0.07
     apreci
    -0.07
     गठन
    -0.07
    cles
    -0.07
    /Re
    -0.07
    POSITIVE LOGITS
    大量
    0.10
     بيانات
    0.09
     데이터를
    0.09
     samples
    0.08
     داده
    0.08
     pia
    0.08
     données
    0.08
     المصادر
    0.07
    ข้อมูล
    0.07
     sewage
    0.07
    Act Density 0.004%

    No Known Activations