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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ा↵
    -0.07
     bait
    -0.07
    试
    -0.07
    Group
    -0.06
    rances
    -0.06
     Standard
    -0.06
    uty
    -0.06
    ERICA
    -0.06
    edor
    -0.06
    etleri
    -0.06
    POSITIVE LOGITS
     lựa
    0.07
     �
    0.06
    #af
    0.06
     Elves
    0.06
     бороть
    0.06
     kol
    0.06
    mmc
    0.06
     сдел
    0.06
    paque
    0.06
    ρισ
    0.06
    Act Density 0.017%

    No Known Activations