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

    Neuronpedia

    INDEX
    Explanations

    numerical values or digits related to time and quantity

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

    numbers followed by units or classifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     []:
    -0.41
    <i>
    -0.39
    <strong>
    -0.34
    All
    -0.34
    <sup>
    -0.33
    <em>
    -0.33
    Õ
    -0.33
    <b>
    -0.32
    Line
    -0.32
     çat
    -0.32
    POSITIVE LOGITS
    তথ্যসূত্র
    0.91
    <?
    0.77
     المعيارى
    0.77
    WebElementEntity
    0.73
    iſchen
    0.72
    ientras
    0.72
    niſſe
    0.71
    hubanes
    0.69
     Verſ
    0.69
     HttpNotFound
    0.69
    Act Density 0.010%

    No Known Activations