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

    Neuronpedia

    INDEX
    Explanations

    igh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kt
    -0.07
     tốc
    -0.07
     Tat
    -0.07
     nutrients
    -0.07
    包
    -0.07
    만원
    -0.07
     '"
    -0.07
     mát
    -0.07
     Jacket
    -0.07
    ylie
    -0.07
    POSITIVE LOGITS
     weigh
    0.15
     weighing
    0.14
     weighs
    0.14
     weighed
    0.12
    weigh
    0.09
    負
    0.07
     outweigh
    0.07
     ponder
    0.07
     undermine
    0.07
    /__
    0.07
    Act Density 0.005%

    No Known Activations