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

    Neuronpedia

    INDEX
    Explanations

    application / use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alternativa
    0.41
     alternativ
    0.38
    dependencies
    0.38
    ദ്ര
    0.38
     compensate
    0.38
     informieren
    0.38
     सफाया
    0.37
     informativa
    0.37
    Attrs
    0.37
    Alessandro
    0.37
    POSITIVE LOGITS
     application
    1.59
    应用
    1.49
     применения
    1.48
     적용
    1.48
     aplic
    1.45
     применение
    1.45
     Application
    1.42
     aplicación
    1.42
     تطبيق
    1.41
    application
    1.40
    Act Density 0.009%

    No Known Activations