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

    Neuronpedia

    INDEX
    Explanations

    book titles and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    置
    -0.08
    ᠴ
    -0.07
    สาย
    -0.07
    螨
    -0.07
    wise
    -0.07
    pton
    -0.06
    镐
    -0.06
     д
    -0.06
    ант
    -0.06
    лит
    -0.06
    POSITIVE LOGITS
     outfield
    0.07
     Buddhism
    0.07
    NotSupportedException
    0.07
     ]↵
    0.07
     سبح
    0.06
    utorial
    0.06
     polls
    0.06
    场比赛
    0.06
     UIView
    0.06
     portraits
    0.06
    Act Density 0.027%

    No Known Activations