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

    Neuronpedia

    INDEX
    Explanations

    frameworks or contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AYER
    -0.07
     online
    -0.06
     lut
    -0.06
     Gem
    -0.06
     mills
    -0.06
     mill
    -0.06
     نیر
    -0.06
     reflecting
    -0.06
    writer
    -0.06
     يع
    -0.06
    POSITIVE LOGITS
     Rahmen
    0.10
     рамках
    0.08
    (Room
    0.07
    sanitize
    0.07
     gerçekleş
    0.07
     ไทย
    0.07
    ___
    0.06
    ถาน
    0.06
    erals
    0.06
    >k
    0.06
    Act Density 0.021%

    No Known Activations