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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Distrib
    -0.09
     Lexus
    -0.08
     trở
    -0.08
    漫步
    -0.08
    屏幕
    -0.07
    ortex
    -0.07
     Due
    -0.07
    عبر
    -0.07
     is
    -0.07
    From
    -0.07
    POSITIVE LOGITS
     that
    0.18
    that
    0.11
     That
    0.09
     أنه
    0.09
    “That
    0.08
    컁
    0.08
    "That
    0.08
     THAT
    0.08
     что
    0.07
    会见
    0.07
    Act Density 0.675%

    No Known Activations