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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects formal medical diagnostic or staging terms (e.g., “diagnosis,” “stage,” etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     compartir
    -0.07
    azaar
    -0.07
    Rows
    -0.07
    _cluster
    -0.07
    FontSize
    -0.06
     walking
    -0.06
    _Show
    -0.06
    rowable
    -0.06
    ([]*
    -0.06
     варі
    -0.06
    POSITIVE LOGITS
    detect
    0.07
     psychiatric
    0.07
    수가
    0.06
    rgyz
    0.06
     Citation
    0.06
     nächsten
    0.06
     doubt
    0.06
     quantitative
    0.06
     eğit
    0.06
    =d
    0.06
    Act Density 0.013%

    No Known Activations