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

    Neuronpedia

    INDEX
    Explanations

    Sequ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    most
    -0.06
     arch
    -0.06
     зам
    -0.06
     Exercise
    -0.06
     purchased
    -0.06
     distribution
    -0.06
    pull
    -0.06
    sigmoid
    -0.06
     ped
    -0.06
    (original
    -0.06
    POSITIVE LOGITS
    UU
    0.07
     NXT
    0.07
     世
    0.06
    Dou
    0.06
    -I
    0.06
    ovně
    0.06
    ген
    0.06
     ：
    0.06
     Tenn
    0.06
    ีเด
    0.06
    Act Density 0.012%

    No Known Activations