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

    Neuronpedia

    INDEX
    Explanations

    glob

    np_max-act · gemini-2.0-flash

    This neuron fires most strongly on occurrences of the Python “glob” module name (i.e. the token glob).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Protein
    -0.08
    字符串
    -0.07
     recordings
    -0.07
    .Download
    -0.06
     WATCH
    -0.06
     Giovanni
    -0.06
     protein
    -0.06
    ажд
    -0.06
     LaTeX
    -0.06
    	with
    -0.06
    POSITIVE LOGITS
     ble
    0.07
     sensed
    0.06
     volatility
    0.06
     preferredStyle
    0.06
    atched
    0.06
     karşısında
    0.06
    ่ำ
    0.06
     (*(
    0.06
    mek
    0.06
     repeating
    0.06
    Act Density 0.009%

    No Known Activations