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

    Neuronpedia

    INDEX
    Explanations

    instances of lemmas and mathematical notation in the text

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

    mathematical lemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.54
     $("
    -0.44
    SystemColors
    -0.43
     protoimpl
    -0.41
    windowFixed
    -0.41
    ValueGeneration
    -0.40
    (");
    -0.40
    Eacute
    -0.40
    yves
    -0.40
    total
    -0.40
    POSITIVE LOGITS
    lemma
    2.33
    Lemma
    2.25
     lemma
    2.23
     Lemma
    2.05
     lemmas
    1.55
    LEMMA
    1.52
     theorem
    0.90
     lema
    0.89
     Theorem
    0.88
    Theorem
    0.81
    Act Density 0.018%

    No Known Activations