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

    Neuronpedia

    INDEX
    Explanations

    medical terminology related to cancer and its treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "cancer"

    np_acts-logits-general · gemini-2.0-flash

    cancer types and stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsStream
    -0.66
     Ouverture
    -0.64
    DispatchToProps
    -0.60
    tschaft
    -0.59
     fainted
    -0.58
     configureStore
    -0.58
    +:+
    -0.58
    клопе
    -0.58
    HttpPut
    -0.58
    ]]
    -0.58
    POSITIVE LOGITS
     cancer
    1.07
     Cancer
    0.88
     cancers
    0.87
     CANCER
    0.86
    Cancer
    0.85
     tumor
    0.85
     cancerous
    0.82
     cáncer
    0.81
     malignant
    0.81
     carcinoma
    0.80
    Act Density 0.737%

    No Known Activations