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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hann
    -0.07
     youth
    -0.07
     tavern
    -0.07
    ніч
    -0.07
    人
    -0.06
     σαν
    -0.06
     gian
    -0.06
     cult
    -0.06
    Nu
    -0.06
     counter
    -0.06
    POSITIVE LOGITS
    izzlies
    0.06
    isinde
    0.06
     �
    0.06
     آماده
    0.06
     comps
    0.06
    注
    0.06
     از
    0.06
     edilmesi
    0.06
     پرونده
    0.06
     فایل
    0.06
    Act Density 0.093%

    No Known Activations