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

    Neuronpedia

    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash

    This neuron fires on first-person case-reporting phrases (e.g. “we report,” “we describe,” etc.) that introduce medical case studies.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    تيار
    -0.07
     клад
    -0.07
    DOCUMENT
    -0.07
     tomu
    -0.06
     WebView
    -0.06
    .db
    -0.06
    _hour
    -0.06
     yourself
    -0.06
    attles
    -0.06
    _kel
    -0.06
    POSITIVE LOGITS
     enticing
    0.07
    _MS
    0.07
     MSI
    0.07
    _roi
    0.06
    ylan
    0.06
    룸
    0.06
    afx
    0.06
     refund
    0.06
    _grid
    0.06
    -dem
    0.06
    Act Density 0.017%

    No Known Activations