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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters used for formatting and structuring information

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

    as followed by mathematical variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centralwidget
    -0.43
    arraycopy
    -0.40
     חיצוניים
    -0.40
    ulary
    -0.40
    fekt
    -0.40
    zept
    -0.39
     tut
    -0.39
    readLine
    -0.38
    WebVitals
    -0.38
    otella
    -0.38
    POSITIVE LOGITS
     as
    0.58
     autorytatywna
    0.54
     ujednoznacz
    0.53
     As
    0.50
     ivelany
    0.47
    As
    0.46
    envolvimento
    0.44
    лтемелер
    0.43
     Histórico
    0.42
     AS
    0.41
    Act Density 0.047%

    No Known Activations