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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and definitions in a formal context

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

    defining terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ActionCreators
    -0.63
    postIndex
    -0.59
    AutoScale
    -0.59
    WriteBarrier
    -0.58
    wahati
    -0.58
    tagHelperRunner
    -0.57
     وتسجيلات
    -0.56
    хьтан
    -0.54
    RegressionTest
    -0.54
    sizeCache
    -0.53
    POSITIVE LOGITS
     define
    1.41
     definition
    1.36
     Define
    1.29
     defined
    1.22
     defines
    1.20
    Define
    1.18
     Definition
    1.17
     definitions
    1.17
     defining
    1.17
     definición
    1.13
    Act Density 0.155%

    No Known Activations