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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    1.23
     all
    1.10
    in
    1.07
     এমন
    1.02
     as
    1.00
     for
    0.98
     in
    0.97
     at
    0.93
    在
    0.93
     this
    0.93
    POSITIVE LOGITS
     ہے۔
    1.06
    ﺎ
    0.96
    ۔
    0.96
     nieco
    0.96
     dekor
    0.95
    ու
    0.93
    0
    0.93
     می‌باشد
    0.91
    感じです
    0.90
     =)
    0.87
    Act Density 1.026%

    No Known Activations