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

    Neuronpedia

    INDEX
    Explanations

    living

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Es
    -0.08
     colours
    -0.08
     Ethiopia
    -0.07
    центр
    -0.07
    畢竟
    -0.07
    排名
    -0.07
     remains
    -0.07
     conseguir
    -0.07
     obtain
    -0.07
     רבים
    -0.07
    POSITIVE LOGITS
     mystical
    0.07
    Matchers
    0.07
    所说的
    0.07
    (permission
    0.07
     raging
    0.07
    Amazing
    0.07
    Asset
    0.06
     Interactive
    0.06
    inished
    0.06
    MAR
    0.06
    Act Density 0.002%

    No Known Activations