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

    Neuronpedia

    INDEX
    Explanations

    assignment of quoted strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stall
    0.62
    кість
    0.62
     UNC
    0.57
    හි
    0.57
     pomiesz
    0.57
     করিবার
    0.57
     அழைத்து
    0.57
     न्यायालयाने
    0.56
    に関する法律
    0.56
    靝
    0.56
    POSITIVE LOGITS
     "
    2.48
    ("
    2.42
     '
    2.29
    ('
    2.28
     `"
    2.18
     “
    2.07
     '"
    2.06
     ("
    2.02
     `'
    1.98
     ('
    1.96
    Act Density 0.624%

    No Known Activations