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

    Neuronpedia

    INDEX
    Explanations

    Tracking patients until date

    np_max-act · gemini-2.0-flash

    This neuron activates on words that mark temporal progression or follow-up in cohort studies—terms like “followed,” “until,” “first,” and related timing indicators.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     наших
    -0.07
     apopt
    -0.07
    >Add
    -0.06
     každé
    -0.06
     staat
    -0.06
    一定
    -0.06
    _^(
    -0.06
    .Reader
    -0.06
    .Protocol
    -0.06
    )localObject
    -0.06
    POSITIVE LOGITS
     successors
    0.07
     زیست
    0.07
    ilha
    0.07
    IGHL
    0.06
    _I
    0.06
     läng
    0.06
    ają
    0.06
    τία
    0.06
    한
    0.06
    менш
    0.06
    Act Density 0.006%

    No Known Activations