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

    Neuronpedia

    INDEX
    Explanations

    file access modes

    np_max-act · gemini-2.0-flash

    The neuron fires on Python file‐writing code—particularly on calls to write() and open() with write/append modes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _SECRET
    -0.07
     derivative
    -0.07
    .time
    -0.07
     editText
    -0.06
    <vector
    -0.06
     Aster
    -0.06
    	debug
    -0.06
     LOG
    -0.06
     مهر
    -0.06
    ктив
    -0.06
    POSITIVE LOGITS
     руч
    0.07
     Osw
    0.07
     courte
    0.07
     onslaught
    0.06
     هو
    0.06
     샤
    0.06
    `)↵
    0.06
    __;
    0.06
     겨
    0.06
     منها
    0.06
    Act Density 0.007%

    No Known Activations