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

    Neuronpedia

    INDEX
    Explanations

    placing things or locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    1.38
    {
    1.38
    2
    1.17
    and
    1.02
    4
    1.01
    a
    0.98
    la
    0.98
    5
    0.94
    7
    0.91
     by
    0.88
    POSITIVE LOGITS
    ल
    1.01
    υτό
    0.98
    ਾਈ
    0.91
    ेंट्स
    0.88
     coloque
    0.85
     It
    0.81
    urized
    0.81
     crucifixion
    0.81
    ન
    0.80
    م
    0.79
    Act Density 0.041%

    No Known Activations