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

    Neuronpedia

    INDEX
    Explanations

    references to specific quantities and comparisons in data

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

    percentages and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h1>
    -0.56
    <h2>
    -0.45
    Bis
    -0.40
    <
    -0.39
    tagHelperRunner
    -0.36
    #!/
    -0.35
    <h3>
    -0.35
    [
    -0.35
    Work
    -0.34
    Vol
    -0.34
    POSITIVE LOGITS
    ConstraintMaker
    0.73
     مرئيه
    0.69
    OGND
    0.68
    ContentAsync
    0.65
    enderror
    0.62
     متعلقه
    0.62
    ViewImports
    0.60
    Referanser
    0.60
    GEBURTS
    0.59
    SequentialGroup
    0.59
    Act Density 0.076%

    No Known Activations