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

    Neuronpedia

    INDEX
    Explanations

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {}'.
    0.33
    leyebilirsiniz
    0.29
    imaan
    0.29
    {}".
    0.29
    BURG
    0.28
     گئی۔
    0.28
    MINUTE
    0.28
    ebilirsiniz
    0.28
    COUNTRY
    0.27
    μένο
    0.27
    POSITIVE LOGITS
     ,
    0.49
     &
    0.48
     and
    0.40
    ,
    0.38
    、
    0.38
     et
    0.34
     ...,
    0.34
     \
    0.34
     $,
    0.33
     all
    0.32
    Act Density 0.765%

    No Known Activations