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

    Neuronpedia

    INDEX
    Explanations

    experiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     düzen
    -0.07
    igte
    -0.06
     керів
    -0.06
    ั
    -0.06
    urga
    -0.06
    <<"
    -0.06
     foe
    -0.06
     público
    -0.06
     zby
    -0.06
     thép
    -0.06
    POSITIVE LOGITS
     음
    0.07
     Thường
    0.07
     es
    0.07
    Deleting
    0.07
     Harmon
    0.07
     Indianapolis
    0.07
     "",
↵
    0.06
    서울
    0.06
     gsl
    0.06
     khỏ
    0.06
    Act Density 0.002%

    No Known Activations