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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash

    This neuron detects the phrases where a study reports which patients (or cases) “were … included/identified/enrolled” (i.e. the inclusion of participants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ("~
    -0.07
    ensis
    -0.07
     QRect
    -0.07
     thor
    -0.06
    FU
    -0.06
     F
    -0.06
     Quartz
    -0.06
    _syntax
    -0.06
     Hashtable
    -0.06
    안
    -0.06
    POSITIVE LOGITS
     Westminster
    0.07
    /wiki
    0.07
     korum
    0.06
     بین
    0.06
     khám
    0.06
     DVDs
    0.06
    popular
    0.06
    578
    0.06
    ρα
    0.06
    They
    0.06
    Act Density 0.016%

    No Known Activations