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

    Neuronpedia

    INDEX
    Explanations

    BUY

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that refer to product/version markers—e.g. the “BUY” call-to-action and model version numbers like “3.5.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    に関
    -0.07
    ーテ
    -0.07
     faç
    -0.06
     Jab
    -0.06
     governing
    -0.06
    ενο
    -0.06
    ibBundleOrNil
    -0.06
    lédl
    -0.06
     windshield
    -0.06
    َب
    -0.06
    POSITIVE LOGITS
    ousy
    0.07
    rende
    0.06
    *-
    0.06
    (image
    0.06
     Assist
    0.06
    _Sh
    0.06
    Dialogue
    0.06
    .crypto
    0.06
    .strategy
    0.06
    -conf
    0.06
    Act Density 0.000%

    No Known Activations