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

    Neuronpedia

    INDEX
    Explanations

    invention

    np_max-act · gemini-2.0-flash

    This neuron detects patent‐style boilerplate phrasing announcing what “the present invention relates to.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (/^
    -0.08
     cache
    -0.07
    |--
    -0.07
     itm
    -0.07
     judicial
    -0.07
     Puzzle
    -0.06
    -normal
    -0.06
     chore
    -0.06
     stalls
    -0.06
    enger
    -0.06
    POSITIVE LOGITS
    addColumn
    0.07
    .getBody
    0.07
    witter
    0.06
     &___
    0.06
    ylie
    0.06
    veled
    0.06
     ValueEventListener
    0.06
     SHR
    0.06
     thinly
    0.06
    Founder
    0.06
    Act Density 0.010%

    No Known Activations