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

    Neuronpedia

    INDEX
    Explanations

    gcc, ++

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spotting compiler toolchain terms—words and flags related to compiling and linking code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _One
    -0.07
    iqué
    -0.06
    _REPEAT
    -0.06
     Rey
    -0.06
    Handlers
    -0.06
    Kir
    -0.06
    _kernel
    -0.06
    istem
    -0.06
    hevik
    -0.06
    áním
    -0.06
    POSITIVE LOGITS
     Scarlet
    0.06
     IonicPage
    0.06
     coatings
    0.06
    erland
    0.06
    formation
    0.06
     sometime
    0.06
    	DBG
    0.06
     structures
    0.06
    elsen
    0.06
     aur
    0.06
    Act Density 0.009%

    No Known Activations