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

    Neuronpedia

    INDEX
    Explanations

    compliance

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of patients’ (or study) medication adherence/compliance.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     neur
    -0.07
     elde
    -0.07
    _rec
    -0.06
     blocked
    -0.06
     liter
    -0.06
     Surg
    -0.06
     poisonous
    -0.06
     favor
    -0.06
     burial
    -0.06
     scrambled
    -0.06
    POSITIVE LOGITS
     adherence
    0.08
        
↵    
↵
    0.07
     mettre
    0.07
     chấm
    0.06
    契
    0.06
     ليس
    0.06
    χν
    0.06
    edik
    0.06
    σε
    0.06
    mers
    0.06
    Act Density 0.008%

    No Known Activations