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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash

    This neuron detects numeric position metadata in parsed-AST nodes (e.g. the “loc”, “start”, “end”, line/column, and range values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    atre
    -0.06
    species
    -0.06
     Раз
    -0.06
     Archae
    -0.06
     Simpsons
    -0.06
    ouched
    -0.06
    oke
    -0.06
     Infrastructure
    -0.06
    fad
    -0.06
     commissioners
    -0.06
    POSITIVE LOGITS
    	logger
    0.07
    FileNotFoundException
    0.06
     Орг
    0.06
    STEM
    0.06
    LOT
    0.06
     mentioning
    0.06
    IPLE
    0.06
     prend
    0.06
    ALTH
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations