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

    Neuronpedia

    INDEX
    Explanations

    serialize

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to object serialization (e.g. “Serialize,” “serial,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    800
    -0.07
     obras
    -0.07
    793
    -0.07
     باغ
    -0.07
    536
    -0.07
     bốn
    -0.07
     inhabited
    -0.06
    ๒
    -0.06
     sees
    -0.06
     psychiatrist
    -0.06
    POSITIVE LOGITS
    Serializer
    0.09
    patible
    0.07
    Serialize
    0.07
    SDK
    0.07
    ーカー
    0.07
    stered
    0.07
    \Helpers
    0.07
    σί
    0.06
    _serializer
    0.06
    аторы
    0.06
    Act Density 0.006%

    No Known Activations