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

    Neuronpedia

    INDEX
    Explanations

    frequency='D'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     letech
    0.47
     հատ
    0.43
     المقام
    0.42
    ഽ
    0.41
     cancers
    0.41
     ล้าน
    0.41
     Бүген
    0.41
     الخاص
    0.40
     legno
    0.39
     edição
    0.39
    POSITIVE LOGITS
    納
    0.44
    نامج
    0.41
    ர்க்க
    0.38
    ruppe
    0.38
    ፁ
    0.38
     leash
    0.37
    казыва
    0.37
    alik
    0.37
     மூட
    0.37
     selesai
    0.36
    Act Density 0.001%

    No Known Activations