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

    Neuronpedia

    INDEX
    Explanations

    int-based sound or spelling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.46
     was
    1.41
    in
    1.36
    re
    1.26
     is
    1.25
    was
    1.20
    m
    1.16
    น
    1.16
    an
    1.15
    is
    1.09
    POSITIVE LOGITS
    4
    1.16
    ला
    1.03
     ਨ
    1.00
    US
    0.98
     불구하고
    0.97
     разрабо
    0.95
    ள்ளனர்
    0.94
     dolayı
    0.90
     be
    0.89
    ние
    0.89
    Act Density 0.335%

    No Known Activations