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

    Neuronpedia

    INDEX
    Explanations

    ization

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of hospital‐ or healthcare‐related utilization events (e.g., hospitalizations, admissions, emergency room visits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     params
    -0.07
    _byte
    -0.07
    _ll
    -0.07
     desks
    -0.07
     Point
    -0.06
     ecosystem
    -0.06
     Faith
    -0.06
     Edit
    -0.06
    (buf
    -0.06
     QPainter
    -0.06
    POSITIVE LOGITS
    listed
    0.07
     Kendrick
    0.06
     Senator
    0.06
     SIL
    0.06
     alarmed
    0.06
    ıyorlar
    0.06
    regular
    0.06
     vå
    0.06
    $ar
    0.06
    (TM
    0.06
    Act Density 0.016%

    No Known Activations