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

    Neuronpedia

    INDEX
    Explanations

    technical terms and discussions related to planning and optimizing processes

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

    preparation, life, biology, experience

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

    the neuron detects topic-bearing content words (key nouns/adjectives/phrases that indicate the subject or domain of a passage).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.56
     يتيمه
    -0.46
    principalTable
    -0.45
    tershire
    -0.44
    SOUNDBITE
    -0.44
     poichè
    -0.41
    EFIAPI
    -0.40
     tartalomajánló
    -0.39
    ніципалі
    -0.39
     precisione
    -0.39
    POSITIVE LOGITS
    viewDidLoad
    0.49
    IContainer
    0.47
    SharedCtor
    0.46
    writeField
    0.45
    Lähteet
    0.44
    的一切
    0.44
    +#+#
    0.44
     createState
    0.42
     fundamentals
    0.42
    gamesh
    0.41
    Act Density 0.206%

    No Known Activations