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

    Neuronpedia

    INDEX
    Explanations

    text splitting and model loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     காட்சிகள்
    0.41
     état
    0.40
     состояние
    0.40
     состояния
    0.39
     estado
    0.39
     racines
    0.39
     yönet
    0.38
     வகைகள்
    0.38
     asunto
    0.38
     состоянии
    0.37
    POSITIVE LOGITS
    ConformanceMode
    0.49
    PasswordEncoder
    0.46
    ListIterator
    0.43
    Binary
    0.42
    PagerAdapter
    0.42
    DataLoader
    0.42
     adaptive
    0.40
    StackNavigator
    0.40
    SessionFactory
    0.40
    FileWriter
    0.40
    Act Density 0.004%

    No Known Activations