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

    Neuronpedia

    INDEX
    Explanations

    Informal conversations/questions

    np_max-act · gemini-2.0-flash

    medical advice regarding symptoms and interactions with medications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on mentions of medical or healthcare contexts, such as references to doctors, symptoms, treatment, or seeking medical advice.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
     안
    -0.07
    ibar
    -0.06
     din
    -0.06
    Solo
    -0.06
     eigen
    -0.06
    ()]
    -0.06
     піз
    -0.06
    addGroup
    -0.06
    Han
    -0.06
    POSITIVE LOGITS
     Rangers
    0.07
     scrapped
    0.06
    ussed
    0.06
     Xã
    0.06
     ไทย
    0.06
     прост
    0.06
     Love
    0.06
     distinguishing
    0.06
     كام
    0.06
    檢
    0.06
    Act Density 0.031%

    No Known Activations