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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and punctuation marks in mathematical contexts

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

    theorems/equations (e.g., [@KM], Lemma 3.39)

    np_acts-logits-general · gemini-2.0-flash

    citations to theorems and propositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    -0.73
    "
    -0.66
    /
    -0.65
    ,
    -0.62
     оригіналу
    -0.60
    <
    -0.58
    setVerticalGroup
    -0.57
    =
    -0.54
    )
    -0.54
     بيها
    -0.54
    POSITIVE LOGITS
    1
    0.72
     Toda
    0.61
    2
    0.61
     Bohr
    0.57
    3
    0.56
     Öffentlichkeit
    0.55
    xii
    0.55
    énie
    0.55
    Xna
    0.54
     actionMode
    0.54
    Act Density 0.279%

    No Known Activations