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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

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

    threads and thread states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [
    -0.37
     [
    -0.31
    Thief
    -0.30
    .[
    -0.29
    (
    -0.28
     or
    -0.27
     examiner
    -0.27
    ton
    -0.27
    /
    -0.27
    Oval
    -0.26
    POSITIVE LOGITS
    InitVars
    0.88
     AssemblyCulture
    0.81
    ésultats
    0.81
     يتيمه
    0.81
    AddTagHelper
    0.80
    UserScript
    0.78
    OGND
    0.77
    Diweddarwch
    0.74
     '\\;'
    0.74
     queſta
    0.72
    Act Density 0.021%

    No Known Activations