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

    Neuronpedia

    INDEX
    Explanations

    software dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्तिष्क
    0.43
    侕
    0.43
    क्टी
    0.42
     ಸುದ್ದಿ
    0.41
    utzer
    0.41
    hlas
    0.41
     cuisses
    0.40
    StatusCodes
    0.39
     изготов
    0.39
     escenas
    0.38
    POSITIVE LOGITS
     dependencies
    1.59
     dependency
    1.48
     Dependencies
    1.43
    dependencies
    1.39
     Dependency
    1.39
    Dependencies
    1.34
    dependency
    1.34
    Dependency
    1.21
    依赖
    1.19
     dependence
    1.18
    Act Density 0.016%

    No Known Activations