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

    Neuronpedia

    INDEX
    Explanations

    acquaintance

    np_max-act · gemini-2.0-flash

    The neuron chiefly activates on standalone numeric tokens—that is, any digits or numbers appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    factors related to product reviews and customer experiences.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    싸
    -0.06
    azaar
    -0.06
    Handlers
    -0.06
    being
    -0.06
     Maintenance
    -0.06
     ženy
    -0.06
    ayi
    -0.06
     giữ
    -0.06
    /></
    -0.06
    الك
    -0.06
    POSITIVE LOGITS
    (express
    0.07
    chai
    0.07
     Crushing
    0.06
    _ACCESS
    0.06
    ्तक
    0.06
    .BL
    0.06
     organizer
    0.06
    юр
    0.06
     �
    0.06
    <?=
    0.06
    Act Density 1.004%

    No Known Activations