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

    Neuronpedia

    INDEX
    Explanations

    networking layers

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “PDU” (Protocol Data Unit) and related protocol layer terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     чт
    -0.07
     Hanson
    -0.06
     Outcome
    -0.06
     {};↵
    -0.06
     mne
    -0.06
    Jan
    -0.06
     Wy
    -0.06
     Shard
    -0.06
    Hall
    -0.06
     aboard
    -0.06
    POSITIVE LOGITS
     ApplicationContext
    0.07
    .schedulers
    0.07
    تان
    0.07
     adaptations
    0.07
    كي
    0.07
     xong
    0.07
    operations
    0.07
    (Environment
    0.07
     MERCHANTABILITY
    0.06
    -performance
    0.06
    Act Density 0.009%

    No Known Activations