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

    Neuronpedia

    INDEX
    Explanations

    Disk partitions

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurements and counts (e.g. sizes, sector counts, cylinder/head values) in disk-related command output.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LeBron
    -0.07
     yaygın
    -0.06
     Odyssey
    -0.06
    WAIT
    -0.06
     BroadcastReceiver
    -0.06
    trip
    -0.06
    unu
    -0.06
    Disconnected
    -0.06
    �력
    -0.06
    omb
    -0.06
    POSITIVE LOGITS
    イ
    0.07
    =output
    0.06
    Cole
    0.06
     соч
    0.06
    이
    0.06
     있습니다
    0.06
    likleri
    0.06
    ж
    0.06
    [loc
    0.06
    лек
    0.06
    Act Density 0.004%

    No Known Activations