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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Complete
    -0.06
    levision
    -0.06
    usuarios
    -0.06
     gode
    -0.06
    argest
    -0.06
     Pivot
    -0.06
     dirt
    -0.06
    yaw
    -0.06
    Rose
    -0.06
     Prior
    -0.06
    POSITIVE LOGITS
    -carousel
    0.07
    ２
    0.07
    '%
    0.07
    .contentOffset
    0.07
     unusually
    0.07
    ４
    0.07
    ΟΡ
    0.06
    )],↵
    0.06
     Dragons
    0.06
    تي
    0.06
    Act Density 0.020%

    No Known Activations