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

    Neuronpedia

    INDEX
    Explanations

    exports

    np_max-act · gemini-2.0-flash

    programming-related syntax and keywords.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on occurrences of the CommonJS “exports” identifier (e.g. in `typeof exports == "object"` checks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     близько
    -0.06
    licence
    -0.06
     pooling
    -0.06
     phủ
    -0.06
     redistributed
    -0.06
    าระ
    -0.06
     Blues
    -0.05
     Zukunft
    -0.05
    urum
    -0.05
     situated
    -0.05
    POSITIVE LOGITS
    .ep
    0.08
    /react
    0.07
    Towards
    0.07
     Emb
    0.07
    ые
    0.07
     yapılan
    0.07
    [list
    0.06
    itar
    0.06
    ้องก
    0.06
    шим
    0.06
    Act Density 0.000%

    No Known Activations