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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vietnamese
    -0.08
    unei
    -0.07
     Lithuania
    -0.07
    Nama
    -0.07
    봐
    -0.06
    DataService
    -0.06
     Rena
    -0.06
     Luxury
    -0.06
    Aggregate
    -0.06
     kWh
    -0.06
    POSITIVE LOGITS
     обычно
    0.07
     реп
    0.06
    …but
    0.06
     cooked
    0.06
     xsi
    0.06
     фут
    0.06
     м
    0.06
     asks
    0.06
     запит
    0.06
    .ENTER
    0.06
    Act Density 0.025%

    No Known Activations