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

    Neuronpedia

    INDEX
    Explanations

    patent applications

    np_max-act · gemini-2.0-flash

    This neuron detects patent-style section headings and structural markers (e.g. “Field of the Invention,” “Related Art,” numbered headings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /provider
    -0.08
    UR
    -0.07
     Checker
    -0.07
     takes
    -0.07
     MAP
    -0.07
    Fi
    -0.06
    overs
    -0.06
     went
    -0.06
     Fus
    -0.06
    İT
    -0.06
    POSITIVE LOGITS
    aliz
    0.06
    roots
    0.06
    铁路
    0.06
     atmospheric
    0.06
     salary
    0.06
    ิทธ
    0.06
    adro
    0.06
     Insert
    0.06
     ramp
    0.06
    .equalTo
    0.05
    Act Density 0.001%

    No Known Activations