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

    Neuronpedia

    INDEX
    Explanations

    meta

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of on-page SEO HTML elements—especially title tags, meta descriptions, and image alt tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     spe
    -0.07
    vars
    -0.06
    .Signal
    -0.06
    ndef
    -0.06
    .toolbar
    -0.06
    .Camera
    -0.06
    BED
    -0.06
    borne
    -0.06
    .setHorizontalAlignment
    -0.06
     Sawyer
    -0.06
    POSITIVE LOGITS
    りと
    0.07
     từ
    0.06
    层
    0.06
     observation
    0.06
     paradox
    0.06
     العراق
    0.06
    ae
    0.06
    선
    0.06
    ali
    0.06
    素
    0.06
    Act Density 0.002%

    No Known Activations