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

    Neuronpedia

    INDEX
    Explanations

    invention

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “invention” (typically in patent section headings like “The invention relates to …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     send
    -0.06
     patient
    -0.06
    po
    -0.06
     Auch
    -0.06
    _));↵
    -0.06
     PAL
    -0.06
    =torch
    -0.06
     raids
    -0.06
    essa
    -0.06
     needy
    -0.06
    POSITIVE LOGITS
    řád
    0.07
     Hex
    0.07
    età
    0.07
     яб
    0.06
    取得
    0.06
     ženy
    0.06
     setTimeout
    0.06
     Gifts
    0.06
     hObject
    0.06
     adventurer
    0.06
    Act Density 0.009%

    No Known Activations