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

    Neuronpedia

    INDEX
    Explanations

    inventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "group
    -0.06
     так
    -0.06
     교
    -0.06
     commissioner
    -0.06
    _models
    -0.06
    Mana
    -0.06
    옥
    -0.06
     headquartered
    -0.06
    袖
    -0.05
    -range
    -0.05
    POSITIVE LOGITS
     Astro
    0.07
    ώσεις
    0.07
    оги
    0.07
    dued
    0.07
     keyword
    0.07
     />,
    0.06
    nilai
    0.06
    PageIndex
    0.06
    О
    0.06
     Rolex
    0.06
    Act Density 0.195%

    No Known Activations