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

    Neuronpedia

    INDEX
    Explanations

    built

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “built-in,” identifying references to built-in methods or functions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.07
     Serious
    -0.07
    Channel
    -0.07
    _indx
    -0.07
     Panther
    -0.06
     Hemisphere
    -0.06
     reducer
    -0.06
    Con
    -0.06
    lero
    -0.06
     Chairs
    -0.06
    POSITIVE LOGITS
     Built
    0.09
     built
    0.09
     gilt
    0.08
    Built
    0.08
     Holt
    0.08
    ilt
    0.08
    кт
    0.08
     название
    0.07
     uit
    0.07
     Bau
    0.07
    Act Density 0.008%

    No Known Activations