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

    Neuronpedia

    INDEX
    Explanations

    sd

    np_max-act · gemini-2.0-flash

    The neuron is mainly detecting occurrences of the “.xsd” XML Schema reference (i.e. the “xsd” schemaLocation tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     بار
    -0.07
     život
    -0.07
    (by
    -0.07
     grantResults
    -0.06
    ları
    -0.06
    .navigationItem
    -0.06
     radioButton
    -0.06
    >K
    -0.06
     patriotic
    -0.06
    ์ส
    -0.06
    POSITIVE LOGITS
     arom
    0.06
    Ref
    0.06
     acids
    0.06
    :)
    0.06
     söyley
    0.06
     concerned
    0.06
    شي
    0.06
     welcomed
    0.06
     guarantee
    0.06
     obtained
    0.06
    Act Density 0.001%

    No Known Activations