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

    Neuronpedia

    INDEX
    Explanations

    paperwork

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of signing or authorizing documents (e.g., “sign,” “signed,” “declaration,” “consent letter,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     clinicians
    -0.07
    隐藏
    -0.07
     disciple
    -0.07
     INSERT
    -0.07
    624
    -0.07
     '::
    -0.07
     Cases
    -0.07
     ::
    -0.07
     SubLObject
    -0.07
    pitch
    -0.07
    POSITIVE LOGITS
     те
    0.07
    (man
    0.07
    _ce
    0.06
     кол
    0.06
     لو
    0.06
     satur
    0.06
    catch
    0.06
     пов
    0.05
    (sr
    0.05
    .setup
    0.05
    Act Density 0.010%

    No Known Activations