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

    Neuronpedia

    INDEX
    Explanations

    mathematical and programming operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    None
    1.55
     None
    1.42
     ["
    1.36
    none
    1.21
    ["
    1.20
     "
    1.13
    ()["
    1.12
     "[
    1.10
     {"
    1.09
    ()"
    1.07
    POSITIVE LOGITS
     Math
    2.02
    Math
    1.94
     Mathf
    1.65
     Maths
    1.47
     math
    1.34
     maths
    1.28
     Mathematics
    1.28
     MATH
    1.23
     parseFloat
    1.23
    MATH
    1.17
    Act Density 0.236%

    No Known Activations