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

    Neuronpedia

    INDEX
    Explanations

    answer depends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كويس
    0.52
     Bukan
    0.51
     الحلو
    0.48
     اله
    0.47
     Fernandez
    0.47
     كوس
    0.47
     韓国
    0.46
    ur
    0.46
    umi
    0.44
     Soh
    0.44
    POSITIVE LOGITS
    ե
    0.45
    центра
    0.44
     brochures
    0.44
     anunciar
    0.44
    ናል
    0.43
    သောအ
    0.43
     resorting
    0.42
    が表示
    0.42
    нее
    0.42
     affrontare
    0.42
    Act Density 0.002%

    No Known Activations