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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    The neuron activates on discussion of checking or handling a subprocess’s return (exit) code—e.g. references to `$?`, exit status, and success vs. failure tests.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    syntax
    -0.08
    corev
    -0.07
     drinks
    -0.07
    луч
    -0.07
     disclosure
    -0.06
     caric
    -0.06
     buffers
    -0.06
    .header
    -0.06
    (cls
    -0.06
    ifar
    -0.06
    POSITIVE LOGITS
    善
    0.07
    ût
    0.06
     Seamless
    0.06
    _GAME
    0.06
     temperature
    0.06
     technicians
    0.06
    >")↵
    0.06
    _Rem
    0.06
     epis
    0.06
     distancia
    0.06
    Act Density 0.026%

    No Known Activations