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

    Neuronpedia

    INDEX
    Explanations

    biochemistry

    np_max-act · gemini-2.0-flash

    The neuron activates on early subword fragments that are common Greek‐ or Latin‐derived prefixes in biomedical terminology (e.g. glyco-, lipo-, phospho-, myo-, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    BUILD
    -0.07
    압
    -0.07
    heck
    -0.07
    Bright
    -0.07
    Length
    -0.07
    FO
    -0.07
    .Match
    -0.07
    анов
    -0.07
    ERC
    -0.07
    इ
    -0.06
    POSITIVE LOGITS
     πα
    0.07
    
    0.06
     tez
    0.06
     строки
    0.06
     iod
    0.06
     socially
    0.06
     Kay
    0.05
    (java
    0.05
    .getExternalStorage
    0.05
    oustic
    0.05
    Act Density 0.249%

    No Known Activations