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

    Neuronpedia

    INDEX
    Explanations

    polynomials and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     computable
    0.95
    崂
    0.91
     quantifying
    0.88
     quantification
    0.85
    鮪
    0.84
    thiaz
    0.82
    婴儿
    0.82
     측정
    0.81
     öl
    0.81
     yogurt
    0.80
    POSITIVE LOGITS
     Polynomial
    1.11
     polinomio
    1.05
     binomial
    1.02
     polynomial
    1.00
    polynomial
    0.98
    Polynomial
    0.97
     factored
    0.96
     polynomials
    0.95
     factorizar
    0.93
     Factors
    0.91
    Act Density 0.173%

    No Known Activations