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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens—case numbers, section citations, dates, monetary amounts, and other digit sequences commonly used in legal documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    antium
    -0.07
    Theo
    -0.06
     Inbox
    -0.06
     slapped
    -0.06
    ITU
    -0.06
    말
    -0.06
     looping
    -0.06
     ----------------------------------------------------------------------↵
    -0.06
    .Split
    -0.06
    -reported
    -0.06
    POSITIVE LOGITS
     지금
    0.07
     ček
    0.07
     річ
    0.06
     espaço
    0.06
         ↵↵
    0.06
     All
    0.06
    Years
    0.06
    相同
    0.06
     знаход
    0.06
    /type
    0.06
    Act Density 0.003%

    No Known Activations