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

    Neuronpedia

    INDEX
    Explanations

    inventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    とか
    -0.06
     cultivated
    -0.06
    оке
    -0.06
    __))↵
    -0.06
    cluding
    -0.06
    .lesson
    -0.06
    昨
    -0.06
    lrt
    -0.06
    /.
    -0.06
     回
    -0.06
    POSITIVE LOGITS
    ステ
    0.07
     TWO
    0.06
    Glass
    0.06
     recourse
    0.06
    plorer
    0.06
     shortest
    0.06
     diện
    0.06
    balances
    0.06
    responsive
    0.06
    divider
    0.06
    Act Density 0.012%

    No Known Activations