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

    Neuronpedia

    INDEX
    Explanations

    component initialization and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     differentiable
    0.43
    Debugging
    0.40
    ＮＡＮＡ
    0.39
    SQLALCHEMY
    0.39
    Celsius
    0.38
     Celsius
    0.38
     набира
    0.37
    楓
    0.37
     lock
    0.36
     लॉक
    0.36
    POSITIVE LOGITS
     components
    1.01
    components
    0.96
     componentes
    0.95
     komponent
    0.94
     Komponenten
    0.91
     komponen
    0.90
     Components
    0.89
     COMPONENTS
    0.89
     компонентов
    0.82
    组件
    0.81
    Act Density 0.001%

    No Known Activations