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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carne
    -0.07
     opposition
    -0.07
     blockIdx
    -0.07
    ляють
    -0.07
     "{\"
    -0.07
     داشت
    -0.07
     Tru
    -0.07
    쓰
    -0.06
    (KeyEvent
    -0.06
    됨
    -0.06
    POSITIVE LOGITS
    .ImageTransparentColor
    0.06
     Frequently
    0.06
     등을
    0.06
    .green
    0.06
    メージ
    0.06
    ographies
    0.06
    eggies
    0.06
    ेकर
    0.06
    (right
    0.05
    ROAD
    0.05
    Act Density 0.624%

    No Known Activations