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

    Neuronpedia

    INDEX
    Explanations

    File permissions

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals specifying file or directory permission modes (e.g. octal mode constants like 070).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [rand
    -0.07
     subur
    -0.07
    ौ
    -0.06
    uisine
    -0.06
    +d
    -0.06
    ПО
    -0.06
    rones
    -0.06
    _coordinates
    -0.06
    (Camera
    -0.06
     Bannon
    -0.06
    POSITIVE LOGITS
     setInput
    0.07
     declare
    0.07
    .addRow
    0.07
    orris
    0.06
     servidor
    0.06
    IBM
    0.06
    ясь
    0.06
    ीप
    0.06
    Ens
    0.06
     CASE
    0.06
    Act Density 0.001%

    No Known Activations