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

    Neuronpedia

    INDEX
    Explanations

    specific markers of chronological or numerical significance

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

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -1.01
    AndEndTag
    -0.96
    Personendaten
    -0.82
    ConstraintMaker
    -0.79
    OGND
    -0.77
    Билгалдахарш
    -0.75
     صوتيه
    -0.75
    IntoConstraints
    -0.75
     autorytatywna
    -0.73
     ویکی‌پدیا
    -0.73
    POSITIVE LOGITS
    摘要
    0.29
     fuel
    0.28
     carburant
    0.24
     Sommer
    0.24
     cur
    0.23
     Thom
    0.23
     transition
    0.23
     im
    0.23
     wear
    0.23
     bowel
    0.23
    Act Density 0.101%

    No Known Activations