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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    interest
    -0.07
    eva
    -0.07
     shirt
    -0.07
     showroom
    -0.07
    icie
    -0.07
    flux
    -0.06
    eries
    -0.06
     observed
    -0.06
     substr
    -0.06
     Kids
    -0.06
    POSITIVE LOGITS
    EFAULT
    0.07
    stalk
    0.06
    .GetCurrentMethod
    0.06
    ynchronously
    0.06
    MemoryWarning
    0.06
    Pi
    0.06
     písem
    0.06
     novembre
    0.06
     Πρω
    0.06
    WARE
    0.06
    Act Density 0.008%

    No Known Activations