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

    Neuronpedia

    INDEX
    Explanations

    quantifiers

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on general-purpose quantifier or scope words (e.g. “many,” “different,” “all,” “for”) that set up broad statements or categories.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     a
    -0.07
     In
    -0.07
    razier
    -0.07
    fono
    -0.07
     On
    -0.07
    to
    -0.07
     Resolution
    -0.06
    гл
    -0.06
     on
    -0.06
    icked
    -0.06
    POSITIVE LOGITS
     for
    0.07
     mystical
    0.07
    有什么
    0.07
     nackt
    0.06
    爭
    0.06
     *(*
    0.06
     用户
    0.06
     Taiwanese
    0.06
    (userName
    0.06
    .tagName
    0.06
    Act Density 0.084%

    No Known Activations