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

    Neuronpedia

    INDEX
    Explanations

    re

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of Python’s regex API (e.g. the `re` module and its functions like `re.sub`, `re.findall`, or the word “regex”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ocolate
    -0.07
     equals
    -0.06
    =z
    -0.06
    =S
    -0.06
    +x
    -0.06
     habits
    -0.06
     Alaska
    -0.06
    guild
    -0.06
    osu
    -0.06
     noble
    -0.06
    POSITIVE LOGITS
    .ExecuteNonQuery
    0.07
    开
    0.07
     relaciones
    0.07
     ENT
    0.07
     geb
    0.06
    ünü
    0.06
     padre
    0.06
    ğen
    0.06
    unexpected
    0.06
    RE
    0.06
    Act Density 0.004%

    No Known Activations