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

    Neuronpedia

    INDEX
    Explanations

    powers, exponents, and factorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डिट
    0.68
     пет
    0.66
     Helen
    0.63
     Simon
    0.59
    ocal
    0.58
     Honors
    0.57
     הרו
    0.56
     আহমেদ
    0.56
    enl
    0.55
     Desert
    0.55
    POSITIVE LOGITS
    ^
    1.10
    ^{
    1.06
    factorial
    1.03
     cubed
    1.02
     factorial
    1.01
    ^(
    1.00
    ToExp
    1.00
     cube
    0.98
     exponential
    0.98
    蕈
    0.98
    Act Density 0.660%

    No Known Activations