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

    Neuronpedia

    INDEX
    Explanations

    properties or math concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brindar
    0.97
     renovation
    0.95
     brinda
    0.95
     Aspects
    0.90
     solidarity
    0.89
    collabor
    0.88
     متخصص
    0.87
     fragrances
    0.86
     gastronomy
    0.86
     telas
    0.85
    POSITIVE LOGITS
     algebraic
    1.08
     polynomial
    1.04
     arithmetic
    1.01
     algebraically
    0.94
     algebra
    0.94
     arbitrary
    0.92
     nonzero
    0.92
     Cauchy
    0.92
    algebra
    0.91
     Euclidean
    0.89
    Act Density 0.168%

    No Known Activations