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

    Neuronpedia

    INDEX
    Explanations

    coding syntax and language constructs related to functions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Variables within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    math equations and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.65
    تقاوى
    -0.64
     AssemblyCulture
    -0.60
     noDo
    -0.55
     intptr
    -0.54
    цездатний
    -0.51
     تضيفلها
    -0.48
     autorytatywna
    -0.46
     <=",
    -0.45
    ViewFeatures
    -0.45
    POSITIVE LOGITS
     eight
    0.47
    CppCodeGen
    0.46
     nine
    0.45
     seven
    0.44
     five
    0.44
     six
    0.43
    setColumns
    0.42
     four
    0.41
     öt
    0.41
     étoient
    0.40
    Act Density 1.952%

    No Known Activations