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

    Neuronpedia

    INDEX
    Explanations

    acknowledgment

    np_max-act · gemini-2.0-flash

    The neuron responds to protocol control keywords—especially names of ARQ schemes and acknowledgement terms like ACK, Selective Repeat, Stop-and-Wait, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ’aut
    -0.07
    .discount
    -0.06
    -unit
    -0.06
    اين
    -0.06
    ering
    -0.06
    634
    -0.06
    .readAs
    -0.06
     goog
    -0.06
    _Font
    -0.06
    驗
    -0.06
    POSITIVE LOGITS
     nosso
    0.07
     materi
    0.06
     Echo
    0.06
    ательно
    0.06
     ness
    0.06
     reports
    0.06
     steadily
    0.06
     Suggestions
    0.06
    ikip
    0.06
    Pk
    0.06
    Act Density 0.006%

    No Known Activations