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

    Neuronpedia

    INDEX
    Explanations

    references to document structure and configuration in a code context

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

    Code, non-sentences, and special characters

    np_acts-logits-general · gemini-2.0-flash

    percentage of, colon or, ur and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.43
     tanto
    -0.43
    ette
    -0.42
    hand
    -0.41
    Short
    -0.41
    üch
    -0.41
    ழ
    -0.41
    ung
    -0.40
    мора
    -0.40
     even
    -0.40
    POSITIVE LOGITS
     صوتيه
    1.03
    Hentet
    0.86
     שוליים
    0.80
    </h6>
    0.78
     للمعارف
    0.77
    tvguidetime
    0.77
     للاسماء
    0.76
     дописавши
    0.76
    adaptiveStyles
    0.76
     بيها
    0.76
    Act Density 0.033%

    No Known Activations