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

    Neuronpedia

    INDEX
    Explanations

    customer service/product reviews

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases describing product support and promotional service offerings (e.g. after-sale services, spare-parts supply, warranties).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    晴
    -0.07
    379
    -0.07
     pairing
    -0.07
     Andy
    -0.06
    Parking
    -0.06
    043
    -0.06
     바이
    -0.06
     Hol
    -0.06
     =======
    -0.06
    Pieces
    -0.06
    POSITIVE LOGITS
    :].
    0.06
    초등학교
    0.06
    THIS
    0.06
     elegant
    0.06
    ).*
    0.06
    ヌ
    0.06
     encount
    0.06
    اهر
    0.06
    سد
    0.06
    /proto
    0.06
    Act Density 0.144%

    No Known Activations