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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that are part of Python traceback lines—especially file paths, module names, and import keywords.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sic
    -0.06
    .inventory
    -0.06
     Delicious
    -0.06
    XMLLoader
    -0.06
    (u
    -0.06
    	ST
    -0.06
    _username
    -0.06
    rees
    -0.06
    uby
    -0.06
    ioc
    -0.06
    POSITIVE LOGITS
    ******
↵
    0.06
    .enum
    0.06
     propTypes
    0.06
     Furn
    0.06
    üme
    0.06
     VLC
    0.06
     ağ
    0.06
    vertime
    0.06
    OLUTION
    0.06
    clud
    0.06
    Act Density 0.008%

    No Known Activations