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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    The neuron activates on HTML `<link>` elements (their tag name and associated attributes) in a document’s head.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     дней
    -0.06
    oreferrer
    -0.06
     pepper
    -0.06
    peri
    -0.06
    uan
    -0.06
     choses
    -0.06
     cc
    -0.06
     controlId
    -0.06
     رد
    -0.06
     bd
    -0.06
    POSITIVE LOGITS
    _cast
    0.07
     LOG
    0.07
    MessageBox
    0.07
    _aa
    0.07
    _ability
    0.07
    .display
    0.07
    ibbon
    0.07
     ام
    0.06
     defaults
    0.06
    _iso
    0.06
    Act Density 0.003%

    No Known Activations