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

    Neuronpedia

    INDEX
    Explanations

    connection closed

    np_max-act · gemini-2.0-flash

    The neuron activates on text describing network/socket connections being closed or terminated.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _AMOUNT
    -0.07
     toxins
    -0.07
    งค
    -0.06
    .getResult
    -0.06
    \Customer
    -0.06
    ılıp
    -0.06
     "','"
    -0.06
    QtCore
    -0.06
     
    -0.06
     chứng
    -0.06
    POSITIVE LOGITS
     recep
    0.07
    –↵↵
    0.07
     spokesperson
    0.07
     clinging
    0.06
     пл
    0.06
     –↵↵
    0.06
     des
    0.06
     daughters
    0.06
     noteworthy
    0.06
     entonces
    0.06
    Act Density 0.013%

    No Known Activations