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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax, particularly in a JavaScript or JSON context

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

    configuration parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.74
    GEBURTSDATUM
    -0.73
     betweenstory
    -0.68
    parsedMessage
    -0.66
    ParallelGroup
    -0.62
     Réponses
    -0.62
    interopRequire
    -0.61
    -0.61
     ویکی‌پدی
    -0.61
     utafitiHapana
    -0.60
    POSITIVE LOGITS
     diatur
    0.36
     rosca
    0.33
     Constitución
    0.33
     döne
    0.30
    __(/*!
    0.29
    рити
    0.28
    зад
    0.28
     Burgen
    0.28
    激
    0.27
    çu
    0.27
    Act Density 0.073%

    No Known Activations