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

    Neuronpedia

    INDEX
    Explanations

    Medical research

    np_max-act · gemini-2.0-flash

    This neuron detects complex multiword biomedical terms and technical noun phrases (e.g. names of diseases, proteins, anatomical features, or procedures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _dictionary
    -0.07
     multiplic
    -0.07
    Clear
    -0.07
    	location
    -0.07
    _BANK
    -0.06
     niños
    -0.06
     цвета
    -0.06
    _proxy
    -0.06
     insisted
    -0.06
    .clear
    -0.06
    POSITIVE LOGITS
    appeared
    0.07
    心里
    0.07
     çalış
    0.06
    	g
    0.06
    已
    0.06
     έ
    0.06
    flatMap
    0.06
     <<-
    0.06
     Todd
    0.06
     investigative
    0.06
    Act Density 0.101%

    No Known Activations