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

    Neuronpedia

    INDEX
    Explanations

    punctuation and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     publik
    0.75
     обстанов
    0.71
    öff
    0.70
     panggilan
    0.68
     Crew
    0.68
     Zuschauer
    0.66
    orean
    0.66
    િમ
    0.65
     ими
    0.65
    เม
    0.65
    POSITIVE LOGITS
     、
    1.13
     ，
    0.91
     ・
    0.91
     ).
    0.90
     ،
    0.89
     ----
    0.89
     。,
    0.89
     .)
    0.83
     。
    0.82
     ."
    0.82
    Act Density 0.368%

    No Known Activations