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

    Neuronpedia

    INDEX
    Explanations

    json error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     її
    0.61
    ሯ
    0.59
     négoci
    0.59
     Petersburg
    0.57
     внутріш
    0.56
     মী
    0.55
     _____________
    0.54
     심
    0.52
    াক্তন
    0.52
    癀
    0.52
    POSITIVE LOGITS
    ت
    1.18
    t
    1.09
    '
    1.06
    т
    0.96
    l
    0.94
    a
    0.90
    d
    0.89
    i
    0.87
    k
    0.85
    e
    0.84
    Act Density 0.001%

    No Known Activations