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

    Neuronpedia

    INDEX
    Explanations

    specification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xy
    -0.07
     cog
    -0.07
    src
    -0.07
    >
    -0.07
    shield
    -0.07
    些什么
    -0.06
     circles
    -0.06
    redi
    -0.06
    还原
    -0.06
    screen
    -0.06
    POSITIVE LOGITS
    (Database
    0.07
    永远不会
    0.07
    .numericUpDown
    0.07
     Restrictions
    0.07
    DIRECT
    0.07
     Guarantee
    0.07
    렌
    0.07
    ኤ
    0.07
     מיד
    0.07
     zwłaszcza
    0.07
    Act Density 0.075%

    No Known Activations