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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    도가
    -0.07
     جهت
    -0.07
    owego
    -0.07
    pages
    -0.07
    628
    -0.06
     sitesinde
    -0.06
     miniature
    -0.06
    Experts
    -0.06
     chút
    -0.06
     rgba
    -0.06
    POSITIVE LOGITS
     punishing
    0.07
    .Go
    0.06
    ,k
    0.06
    CA
    0.06
    rior
    0.06
    ],
    0.06
    -effects
    0.06
    ｭ
    0.06
    告
    0.06
     From
    0.06
    Act Density 0.050%

    No Known Activations