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

    Neuronpedia

    INDEX
    Explanations

    Blockchain transactions inclusion

    np_max-act · gemini-2.0-flash

    This neuron detects language describing miners forming or populating new blocks (e.g. words like “creates,” “put,” “sending,” “transaction,” and “block”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    MK
    -0.07
    patch
    -0.07
    .BatchNorm
    -0.07
    _RX
    -0.06
    _VLAN
    -0.06
    Semaphore
    -0.06
    TextView
    -0.06
    _expiry
    -0.06
    /pp
    -0.06
     wed
    -0.06
    POSITIVE LOGITS
     söy
    0.07
     danger
    0.07
    ÅŸ
    0.07
    (@(
    0.07
    faces
    0.06
     comforting
    0.06
     informational
    0.06
    '];↵↵
    0.06
     estruct
    0.06
     comunic
    0.06
    Act Density 0.010%

    No Known Activations