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

    Neuronpedia

    INDEX
    Explanations

    place

    np_max-act · gemini-2.0-flash

    This neuron activates on document header field labels (like “Date Received,” “Requesting Facility,” “Requesting Physician,” “Collection Time,” etc.) in the medical‐report metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    apikey
    -0.07
    keypress
    -0.07
    odes
    -0.06
    _hours
    -0.06
    _TREE
    -0.06
     mạnh
    -0.06
    ari
    -0.06
    ookeeper
    -0.06
     adap
    -0.06
    Criteria
    -0.06
    POSITIVE LOGITS
    .Last
    0.07
     Doğu
    0.07
     sodom
    0.07
    철
    0.06
     Albany
    0.06
     Ribbon
    0.06
    381
    0.06
     Kč
    0.06
    _cutoff
    0.06
    Mont
    0.06
    Act Density 0.001%

    No Known Activations