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

    Neuronpedia

    INDEX
    Explanations

    Mary followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    어로
    0.48
     sám
    0.46
    畞
    0.46
    ERGY
    0.44
     дня
    0.43
    ຕ້ອງ
    0.42
     trá
    0.42
    वर्ड
    0.41
     ayı
    0.40
     держать
    0.40
    POSITIVE LOGITS
     Magdalene
    0.75
    beth
    0.57
     Jane
    0.56
     Magdal
    0.51
    Jane
    0.50
     Elizabeth
    0.50
     Beth
    0.48
     jane
    0.47
    nissen
    0.46
    vonne
    0.46
    Act Density 0.001%

    No Known Activations