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

    Neuronpedia

    INDEX
    Explanations

    Citations and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accelerator
    -0.07
    .navigation
    -0.07
     consultant
    -0.07
    /docker
    -0.07
    ㌢
    -0.07
    ופן
    -0.06
    ketøy
    -0.06
    中心主任
    -0.06
     Scriptures
    -0.06
     advanced
    -0.06
    POSITIVE LOGITS
    一双
    0.08
     antagon
    0.07
    *x
    0.07
    曾经
    0.07
    ")),↵
    0.07
     regul
    0.07
    ]),
    0.07
     Trit
    0.07
    探し
    0.06
    ')),
    0.06
    Act Density 0.641%

    No Known Activations