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

    Neuronpedia

    INDEX
    Explanations

    blood pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.68
    metrics
    0.60
    在
    0.59
    bukti
    0.58
    ianic
    0.57
    xiety
    0.56
    perturb
    0.55
     в
    0.55
    uttu
    0.54
     in
    0.54
    POSITIVE LOGITS
    ী
    0.95
    ة
    0.87
     projeto
    0.86
     articolo
    0.86
    ı
    0.83
     chuyện
    0.77
    ни
    0.72
    ית
    0.71
    าย
    0.70
     italiano
    0.70
    Act Density 0.001%

    No Known Activations