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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐language code tokens—especially function definitions and object member accesses (e.g. “public,” “function,” “this->,” “db->,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Catalog
    -0.07
    Ћ
    -0.07
     framed
    -0.07
     STANDARD
    -0.07
    vo
    -0.06
    лід
    -0.06
    색
    -0.06
     contempt
    -0.06
    ้นท
    -0.06
     ------------
    -0.06
    POSITIVE LOGITS
     základ
    0.07
    (gameObject
    0.06
     feder
    0.06
    -envelope
    0.06
    /QĐ
    0.06
    >({
    0.06
    "description
    0.05
     Athe
    0.05
     wyn
    0.05
     рівень
    0.05
    Act Density 0.106%

    No Known Activations