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

    Neuronpedia

    INDEX
    Explanations

    рав

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pů
    -0.08
     TOUR
    -0.08
    億
    -0.07
     поперед
    -0.07
     Labour
    -0.07
     filho
    -0.07
    _Offset
    -0.07
    ählt
    -0.07
     SALE
    -0.07
     potassium
    -0.07
    POSITIVE LOGITS
     зд
    0.07
    ㅎ
    0.07
    416
    0.06
     Remain
    0.06
     glad
    0.06
    asdf
    0.06
     YY
    0.05
     дот
    0.05
    „ظ
    0.05
     
↵
↵
    0.05
    Act Density 0.002%

    No Known Activations