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

    Neuronpedia

    INDEX
    Explanations

    code structure elements such as closing brackets and tags

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

    technical programming terms and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hong
    -0.47
    SizeMode
    -0.46
    rittura
    -0.46
     digress
    -0.43
     distract
    -0.42
    Karriere
    -0.42
    ieni
    -0.41
    criture
    -0.41
    jupiter
    -0.41
    en
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.68
    ResumeLayout
    0.65
     ویکی‌پدی
    0.60
    tagHelperRunner
    0.60
     pinulongan
    0.59
    WireFormatLite
    0.55
    IUrlHelper
    0.52
     CanadaChoose
    0.52
     ExecuteAsync
    0.51
     ویکی‌پدیا
    0.49
    Act Density 0.015%

    No Known Activations