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

    Neuronpedia

    INDEX
    Explanations

    structured data and identifiers, particularly in a JSON-like format

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

    dates, times, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.09
    Personendaten
    -0.92
     ویکی‌پدی
    -0.92
    évaluateur
    -0.91
    Personensuche
    -0.87
    IUrlHelper
    -0.84
    :✨
    -0.82
     ویکی‌آمباردا
    -0.82
    transQ
    -0.81
     pleaſure
    -0.81
    POSITIVE LOGITS
     
    0.43
    They
    0.34
     croire
    0.33
    1
    0.32
    2
    0.32
    5
    0.30
    :
    0.29
    The
    0.29
    3
    0.29
    );
    0.29
    Act Density 0.043%

    No Known Activations