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

    Neuronpedia

    INDEX
    Explanations

    order of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    У
    0.70
    ح
    0.64
    S
    0.63
    ها
    0.62
    they
    0.62
    They
    0.59
    ທ່ານ
    0.58
    It
    0.57
    И
    0.56
     Обра
    0.55
    POSITIVE LOGITS
     sorts
    1.37
     course
    1.06
     interest
    0.90
     yester
    0.74
    course
    0.74
     utmost
    0.72
     paramount
    0.72
     indeterminate
    0.70
    quela
    0.69
     our
    0.69
    Act Density 1.027%

    No Known Activations