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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     successive
    -0.07
     remove
    -0.07
     оплач
    -0.07
     removing
    -0.07
     root
    -0.07
     рух
    -0.07
     upstream
    -0.07
     specifying
    -0.07
     slack
    -0.07
     canopy
    -0.07
    POSITIVE LOGITS
     conclusión
    0.09
     또한
    0.09
    总结
    0.08
    Wenn
    0.08
    แกรม
    0.08
     רוצה
    0.08
    herit
    0.08
     강조
    0.08
    此外
    0.08
    oggi
    0.08
    Act Density 0.061%

    No Known Activations