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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    This neuron fires on the boilerplate “invention relates to/related to” phrasing that introduces a patent’s technical‐field description.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Cit
    -0.07
    cit
    -0.07
     Fence
    -0.06
     Devil
    -0.06
    EventData
    -0.06
    ecx
    -0.06
     Evidence
    -0.06
    neas
    -0.06
     ή
    -0.06
     význam
    -0.06
    POSITIVE LOGITS
    UpInside
    0.07
    :indexPath
    0.07
    .imwrite
    0.06
     />';↵
    0.06
    .withOpacity
    0.06
    ')";↵
    0.06
    -parser
    0.06
    !");↵
    0.06
    /yyyy
    0.06
    .ge
    0.06
    Act Density 0.011%

    No Known Activations