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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oluştur
    -0.08
     kir
    -0.08
     хоть
    -0.08
     odmah
    -0.08
    ，比如
    -0.08
     immédi
    -0.07
    'effet
    -0.07
     تؤ
    -0.07
     Howe
    -0.07
     bona
    -0.07
    POSITIVE LOGITS
    期间
    0.10
     દરમ
    0.09
     Daddy
    0.08
     દરમિયાન
    0.08
     teased
    0.08
     dolgo
    0.08
     retom
    0.08
     Attachment
    0.08
    zeitig
    0.07
    ətic
    0.07
    Act Density 0.024%

    No Known Activations