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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical symbols and their associated contexts within scientific data or equations

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

    expressions with caret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PyLong
    -0.53
     <>",
    -0.48
    ArgsConstructor
    -0.47
    цездатний
    -0.46
    stateProvider
    -0.44
    RTEX
    -0.43
    ammans
    -0.43
    ">—
    -0.41
    ombus
    -0.41
    kadot
    -0.40
    POSITIVE LOGITS
     ^
    0.47
     ↑
    0.46
     "^
    0.43
    istoitu
    0.42
    AddTagHelper
    0.42
     /^
    0.41
    にほんブログ村
    0.40
    tagHelperRunner
    0.40
    Strike
    0.40
    compli
    0.39
    Act Density 0.095%

    No Known Activations