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

    Neuronpedia

    INDEX
    Explanations

    underscores and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setPointSize
    0.43
     Naked
    0.41
     ಸ್ಪ
    0.39
    Respect
    0.38
     оско
    0.38
     वक़्त
    0.38
    Look
    0.37
     saber
    0.37
    ill
    0.37
    tiene
    0.37
    POSITIVE LOGITS
     اندراج
    0.45
     により
    0.42
     agric
    0.39
     effluents
    0.39
     cancers
    0.38
     poissons
    0.38
     recipes
    0.38
     denen
    0.38
     bakery
    0.37
     canciones
    0.37
    Act Density 0.003%

    No Known Activations