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

    Neuronpedia

    INDEX
    Explanations

    health condition

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of a patient's medical condition, particularly when described as critical or deteriorating.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     of
    -1.58
    </i>
    -1.45
    </b>
    -1.26
    要不要
    -1.25
    撬
    -1.21
     της
    -1.20
    equ
    -1.19
    ÁCT
    -1.19
     Виктор
    -1.18
    嗬
    -1.18
    POSITIVE LOGITS
     Fasc
    1.27
     mexicana
    1.25
    Neptune
    1.23
     bono
    1.20
     russa
    1.19
     situation
    1.17
     Honig
    1.17
    笃
    1.16
     bich
    1.16
     musica
    1.16
    Act Density 0.038%

    No Known Activations