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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron detects statements expressing a requirement or “need” (e.g. “there is a need for…”) in the patent description.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sent
    -0.07
    =subprocess
    -0.07
    _virtual
    -0.07
     emphasize
    -0.06
     Pett
    -0.06
     locked
    -0.06
    #${
    -0.06
    eltas
    -0.06
     pit
    -0.06
    -find
    -0.06
    POSITIVE LOGITS
     çalışan
    0.07
    ané
    0.07
    cq
    0.07
     getCount
    0.07
    сторія
    0.06
     nam
    0.06
    ('_
    0.06
     рік
    0.06
    pellier
    0.06
    nici
    0.06
    Act Density 0.005%

    No Known Activations