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

    Neuronpedia

    INDEX
    Explanations

    Programming

    np_max-act · gemini-2.0-flash

    references to data types within programming code.

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

    This neuron activates on tokens that name data‐type or component definitions (e.g. record or class identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     кам
    -0.07
     člán
    -0.07
    damage
    -0.07
    (API
    -0.06
    oda
    -0.06
     BehaviorSubject
    -0.06
    lime
    -0.06
     Ř
    -0.06
    servername
    -0.06
    966
    -0.06
    POSITIVE LOGITS
    _Write
    0.07
     misplaced
    0.06
     |/
    0.06
     recurse
    0.06
     Gül
    0.06
    ungen
    0.06
     swirl
    0.06
    較
    0.06
     rally
    0.06
     realtime
    0.06
    Act Density 0.061%

    No Known Activations