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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Regression
    -0.07
    ARTH
    -0.06
     wants
    -0.06
     regression
    -0.06
     established
    -0.06
     vanished
    -0.06
     LinearLayoutManager
    -0.06
     Mapper
    -0.06
    ,color
    -0.06
    Positions
    -0.06
    POSITIVE LOGITS
     chuyên
    0.06
    είτε
    0.06
    >()↵↵
    0.06
     Kuala
    0.06
     nướng
    0.06
    зн
    0.06
    พอ
    0.06
     tüket
    0.06
    .validate
    0.06
     hugely
    0.06
    Act Density 0.017%

    No Known Activations