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

    Neuronpedia

    INDEX
    Explanations

    occurrences of structural notation and delimiters in mathematical expressions

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

    legal declarations

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects document-structure/formatting tokens (e.g., end-of-turn markers and other markup or boundary tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     propOrder
    -0.60
    UserScript
    -0.60
    SharedCtor
    -0.50
    CloseOperation
    -0.49
    TestingModule
    -0.45
    JspWriter
    -0.44
     defaultstate
    -0.43
    GEBURTSDATUM
    -0.43
    RTEE
    -0.43
    featureID
    -0.43
    POSITIVE LOGITS
    }{*}{
    0.56
    0.53
     Вікіпе
    0.52
    labus
    0.50
     ذا
    0.47
    }{*}{}
    0.47
    utti
    0.47
     ""],
    0.47
    ₎
    0.47
    alyptus
    0.46
    Act Density 0.000%

    No Known Activations