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

    Neuronpedia

    INDEX
    Explanations

    heading tags indicating sections or topics within the document

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

    HTML heading tags (h4)

    np_acts-logits-general · gemini-2.0-flash

    "Notes", "Auto", "Consulting", "Simon", "Welcome", "Summary"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    -0.75
    %)$
    -0.69
    adaptiveStyles
    -0.67
    ε
    -0.62
     mies
    -0.61
    writeField
    -0.57
     الرياضيه
    -0.56
     المعيارى
    -0.56
    Hozzáférés
    -0.56
     Ares
    -0.56
    POSITIVE LOGITS
    theless
    1.11
     anúncio
    0.81
    ized
    0.79
    ed
    0.79
    звание
    0.78
    {{\
    0.77
    voorbeeld
    0.76
     Anam
    0.76
    cipated
    0.74
    ."]
    0.73
    Act Density 0.052%

    No Known Activations