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

    Neuronpedia

    INDEX
    Explanations

    quoted speech or citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saya
    0.57
     your
    0.53
    我
    0.53
    咱们
    0.50
     நான்
    0.48
     AND
    0.47
     ANY
    0.47
     உங்கள்
    0.46
     you
    0.46
     tôi
    0.45
    POSITIVE LOGITS
     “[
    1.39
     "...
    1.36
     “…
    1.36
     “‘
    1.26
     "[
    1.25
     "..
    1.20
     "`
    1.11
     "'
    1.09
     “(
    1.05
     unspecified
    1.03
    Act Density 0.005%

    No Known Activations