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

    Neuronpedia

    INDEX
    Explanations

    starting component logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    路径
    0.54
    )}/>
    0.49
     basePath
    0.47
     path
    0.47
    )/
    0.46
     путь
    0.46
     }];
    0.43
    )/\
    0.42
     경로
    0.41
    )]
    0.41
    POSITIVE LOGITS
     element
    0.54
    element
    0.50
     component
    0.48
     components
    0.48
    components
    0.48
     elements
    0.46
     Element
    0.46
    component
    0.44
     элемента
    0.41
     компонен
    0.41
    Act Density 0.000%

    No Known Activations