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

    Neuronpedia

    INDEX
    Explanations

    programming symbols

    np_max-act · gemini-2.0-flash

    This neuron fires on code tokens that look like configuration or option names (e.g. parameter keys, property identifiers) in snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    umpy
    -0.08
    vd
    -0.07
    Months
    -0.07
    ден
    -0.07
     Fan
    -0.07
     meis
    -0.07
     Bing
    -0.06
     vip
    -0.06
    recipe
    -0.06
     длин
    -0.06
    POSITIVE LOGITS
     correspond
    0.07
     interacts
    0.06
    Tesla
    0.06
    _matches
    0.06
     corresponds
    0.06
    doi
    0.06
    https
    0.06
     closure
    0.06
    adlo
    0.06
     passer
    0.06
    Act Density 0.039%

    No Known Activations