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

    Neuronpedia

    INDEX
    Explanations

    chic, stylish, fashionable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    น
    1.67
    ת
    1.57
    a
    1.23
    as
    1.22
    ן
    1.22
     as
    1.10
    ס
    1.05
    นิด
    1.04
    त
    1.02
    n
    0.99
    POSITIVE LOGITS
    在
    1.20
     في
    1.10
     в
    1.06
    ophylline
    1.05
     in
    0.99
     monitors
    0.99
    молу
    0.97
     потери
    0.96
    ٠
    0.94
     majors
    0.93
    Act Density 0.001%

    No Known Activations