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

    Neuronpedia

    INDEX
    Explanations

    Home

    np_max-act · gemini-2.0-flash

    This neuron detects navigation menu links (anchor elements in a nav/header).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pop
    -0.07
    asto
    -0.06
    	op
    -0.06
     Approx
    -0.06
    .answer
    -0.06
     coordination
    -0.06
    ыл
    -0.06
    ovaly
    -0.06
    .scalajs
    -0.06
    erring
    -0.06
    POSITIVE LOGITS
    职业
    0.07
    unned
    0.06
    $',
    0.06
     defective
    0.06
     sexes
    0.06
     pros
    0.06
    _navigation
    0.06
    、「
    0.06
    ได
    0.06
    780
    0.06
    Act Density 0.003%

    No Known Activations