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

    Neuronpedia

    INDEX
    Explanations

    gold standard

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases that name or reference a recognized evaluation benchmark or “standard” (e.g. “gold standard,” “reference standard”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _access
    -0.06
     postings
    -0.06
    ============
    -0.06
     changed
    -0.06
    sap
    -0.06
     roky
    -0.06
    BootApplication
    -0.06
    -width
    -0.06
    izarre
    -0.06
    ukes
    -0.06
    POSITIVE LOGITS
     minOccurs
    0.08
    <count
    0.07
     også
    0.07
    prus
    0.06
    alarm
    0.06
    (INVOKE
    0.06
    ốt
    0.06
    _validator
    0.06
    God
    0.06
     privileged
    0.06
    Act Density 0.005%

    No Known Activations