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

    Neuronpedia

    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash

    The neuron activates on the Python “def” keyword when a function is defined.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    WithOptions
    -0.07
    Layout
    -0.06
    Email
    -0.06
     objected
    -0.06
     LogLevel
    -0.06
     Mex
    -0.06
    ised
    -0.06
    [..
    -0.06
    _Vector
    -0.06
     motivational
    -0.06
    POSITIVE LOGITS
    нообраз
    0.07
    اهرة
    0.07
     ГО
    0.07
    /manual
    0.06
     commissioned
    0.06
     POST
    0.06
     Shopping
    0.06
     hairstyle
    0.06
     makes
    0.06
     (#
    0.06
    Act Density 0.002%

    No Known Activations