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

    Neuronpedia

    INDEX
    Explanations

    polynomials and their powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seafood
    0.52
     ресторан
    0.48
    cadilly
    0.47
    PrivateRoute
    0.46
    高峰
    0.46
    涝
    0.45
    腌
    0.45
    宗教
    0.44
    ゾート
    0.43
    nationality
    0.43
    POSITIVE LOGITS
     polynomials
    2.02
     polynomial
    1.98
     Polynomial
    1.93
    Polynomial
    1.88
    polynomial
    1.79
     monomials
    1.54
     polinomio
    1.54
     polinom
    1.52
     polynom
    1.44
     monomial
    1.41
    Act Density 0.027%

    No Known Activations