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

    Neuronpedia

    INDEX
    Explanations

    user interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Him
    -0.08
     Bennett
    -0.08
     Henri
    -0.08
     hears
    -0.08
     Taylor
    -0.08
     doubtful
    -0.08
    ублик
    -0.08
    төр
    -0.08
     распростран
    -0.07
    niku
    -0.07
    POSITIVE LOGITS
     интерф
    0.14
     interfaz
    0.13
     intuitive
    0.12
    واجهة
    0.12
     redesigned
    0.12
     intuit
    0.12
    布局
    0.11
     agradável
    0.11
     layouts
    0.11
     Oberfläche
    0.10
    Act Density 0.057%

    No Known Activations