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

    Neuronpedia

    INDEX
    Explanations

    words with affixes

    np_max-act · gemini-2.0-flash

    This neuron detects clinical-status descriptors (e.g., “stable,” “chronic”) in medical guideline text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Antique
    -0.07
    標準
    -0.07
     Blocked
    -0.07
    292
    -0.06
     Jihad
    -0.06
    070
    -0.06
     SN
    -0.06
     TextInput
    -0.06
     перей
    -0.06
     začátku
    -0.06
    POSITIVE LOGITS
     kurum
    0.07
    trag
    0.07
    he
    0.07
    iyeti
    0.07
     možné
    0.06
     �
    0.06
    ξη
    0.06
    wild
    0.06
    (Role
    0.06
    riters
    0.06
    Act Density 0.110%

    No Known Activations