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

    Neuronpedia

    INDEX
    Explanations

    Rule

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens—especially decimal numbers as used in legal citations (e.g. “4.38671875” in Rule 36.3).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     traps
    -0.07
     ciz
    -0.06
     GIR
    -0.06
    ACH
    -0.06
    TOR
    -0.06
     coward
    -0.06
     Kr
    -0.06
    691
    -0.06
    Request
    -0.06
    <T
    -0.06
    POSITIVE LOGITS
    ってる
    0.07
    _rand
    0.07
    .addRow
    0.07
    ilinx
    0.06
    Під
    0.06
    \"]
    0.06
    objPHPExcel
    0.06
     Estimate
    0.06
    }',
    0.06
     scrolled
    0.06
    Act Density 0.001%

    No Known Activations