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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash

    The neuron fires on Python code patterns that read a file’s contents into a variable (e.g. calls to file.read() assigned to something).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ACHED
    -0.07
    ляв
    -0.07
    osis
    -0.07
     rady
    -0.07
    airs
    -0.06
    quick
    -0.06
     detox
    -0.06
     resolutions
    -0.06
     Yale
    -0.06
    iros
    -0.06
    POSITIVE LOGITS
    .GetKeyDown
    0.06
     баг
    0.06
     underestimate
    0.06
     olun
    0.06
     grop
    0.06
     gratuite
    0.06
    TextChanged
    0.06
    _startup
    0.06
     अच
    0.06
     tvb
    0.06
    Act Density 0.053%

    No Known Activations