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

    Neuronpedia

    INDEX
    Explanations

    ct

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of surgical procedures and resections (e.g., esophagectomy, gastrectomy, lymphadenectomy, surgical approach).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Macros
    -0.07
    โรงแรม
    -0.06
     груз
    -0.06
     slander
    -0.06
     Trend
    -0.06
     rockets
    -0.06
    是
    -0.06
    �
    -0.06
    详情
    -0.06
     Бор
    -0.06
    POSITIVE LOGITS
    (one
    0.07
     passed
    0.07
     passing
    0.07
    DECLARE
    0.07
    antine
    0.07
    mn
    0.06
    alon
    0.06
    )[:
    0.06
     passes
    0.06
    ])[
    0.06
    Act Density 0.007%

    No Known Activations