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

    Neuronpedia

    INDEX
    Explanations

    PROFITS

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric literals (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _BU
    -0.08
    580
    -0.07
    _RDWR
    -0.07
     Buckley
    -0.06
    .*
    -0.06
     fug
    -0.06
    -Bold
    -0.06
    _flutter
    -0.06
     imz
    -0.06
     Persist
    -0.06
    POSITIVE LOGITS
     onOptionsItemSelected
    0.07
     Westbrook
    0.07
     queried
    0.06
     wasted
    0.06
    ổng
    0.06
     Martha
    0.06
    (num
    0.06
     Voldemort
    0.06
     photographed
    0.06
     llvm
    0.06
    Act Density 0.000%

    No Known Activations