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

    Neuronpedia

    INDEX
    Explanations

    Medical suffixes

    np_max-act · gemini-2.0-flash

    The neuron identifies medical pathology terms—names of diseases or conditions—especially those ending in typical clinical suffixes like “-osis,” “-itis,” or “-asis.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    igans
    -0.09
     elektronik
    -0.07
     Generated
    -0.07
    iação
    -0.06
     практи
    -0.06
    .fx
    -0.06
    _trace
    -0.06
    "strings
    -0.06
     lagi
    -0.06
    haft
    -0.06
    POSITIVE LOGITS
    ydro
    0.06
    prehensive
    0.06
    inen
    0.06
     McA
    0.06
    newInstance
    0.06
    �
    0.06
    挑
    0.06
     кіль
    0.06
     التج
    0.06
     під
    0.06
    Act Density 0.022%

    No Known Activations