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

    Neuronpedia

    INDEX
    Explanations

    .ArgumentParser

    np_max-act · gemini-2.0-flash

    This neuron detects when a Python script calls argparse.ArgumentParser (i.e. the creation of a command‐line argument parser).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    正式
    -0.06
    (cc
    -0.06
    Jos
    -0.06
    dna
    -0.06
     듯
    -0.06
    肌
    -0.06
    蕉
    -0.06
    ่งชาต
    -0.06
    .**************
    -0.06
    营
    -0.06
    POSITIVE LOGITS
    Along
    0.07
    (FILE
    0.07
    _TIMER
    0.06
     friends
    0.06
    �
    0.06
     Fury
    0.06
     Beit
    0.06
     başlamış
    0.06
    lib
    0.06
     charges
    0.06
    Act Density 0.001%

    No Known Activations