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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific numerical or coded formats in the text

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

    "'t", "'s", and "to"

    np_acts-logits-general · gemini-2.0-flash

    't contractions and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.95
    BibitemShut
    -0.75
    期刊论文
    -0.71
    AnchorStyles
    -0.69
    "],
    -0.68
    Espèce
    -0.67
    — 
    -0.67
    )._
    -0.66
    )__
    -0.64
    .。
    -0.63
    POSITIVE LOGITS
    <bos>
    0.80
    SuppressMessage
    0.65
    openzeppelin
    0.59
     isotopes
    0.59
     emeritus
    0.58
     initComponents
    0.58
    webElementXpaths
    0.54
     Emeritus
    0.53
     Olympedia
    0.53
     embassies
    0.52
    Act Density 0.377%

    No Known Activations