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

    Neuronpedia

    INDEX
    Explanations

    Article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Store
    -0.07
    клад
    -0.06
    лена
    -0.06
    >(↵
    -0.06
    .Engine
    -0.06
    Ot
    -0.06
     tả
    -0.06
    вано
    -0.06
    █
    -0.06
     v
    -0.06
    POSITIVE LOGITS
     adept
    0.07
     순간
    0.06
     countless
    0.06
    uitive
    0.06
    TEAM
    0.06
    ﾆ
    0.06
    ([]);↵
    0.06
     Tonight
    0.06
     Brilliant
    0.06
     Hunger
    0.06
    Act Density 0.083%

    No Known Activations