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

    Neuronpedia

    INDEX
    Explanations

    registration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     числа
    -0.07
    dum
    -0.06
    due
    -0.06
    kehr
    -0.06
     Tut
    -0.06
     Вс
    -0.06
    한다
    -0.06
    修改
    -0.06
    ./
    -0.06
    Kon
    -0.06
    POSITIVE LOGITS
     steroid
    0.07
    -operative
    0.07
     liver
    0.06
     */↵↵
    0.06
     Almighty
    0.06
    。」↵↵
    0.06
    -ra
    0.06
    Liver
    0.06
    athering
    0.06
     profession
    0.06
    Act Density 0.005%

    No Known Activations