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

    Neuronpedia

    INDEX
    Explanations

    structural elements or organizational features in documents

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

    Formatting characters like *, -, _, or numbers

    np_acts-logits-general · gemini-2.0-flash

    list items or markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.92
     חיצוניים
    -0.87
    Geplaatst
    -0.86
     وتسجيلات
    -0.80
    mybatisplus
    -0.75
    tagHelperRunner
    -0.73
    basicConfig
    -0.69
    jsonwebtoken
    -0.69
     onPostExecute
    -0.68
    SharedDtor
    -0.68
    POSITIVE LOGITS
    <u>
    0.64
    <strong>
    0.61
    <b>
    0.61
    <em>
    0.53
    <i>
    0.51
     "..\..\
    0.51
    ###
    0.51
    <h3>
    0.51
    <h4>
    0.48
    所谓的
    0.48
    Act Density 0.281%

    No Known Activations