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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    This neuron activates on CamelCase identifiers—especially Lodash’s internal “base” and related function names (e.g. baseIsNative, toInteger, baseClamp) used in require/import calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (MethodImplOptions
    -0.07
    &quot
    -0.07
     cannons
    -0.07
     Inf
    -0.07
     DIN
    -0.07
    _optional
    -0.06
     Maybe
    -0.06
    (DIS
    -0.06
    ".↵↵
    -0.06
     Autonomous
    -0.06
    POSITIVE LOGITS
     truncate
    0.07
    _sd
    0.06
    セット
    0.06
    ista
    0.06
    ISTA
    0.06
    _ble
    0.06
     práva
    0.06
     ciudad
    0.06
    iete
    0.06
    lien
    0.06
    Act Density 0.004%

    No Known Activations