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

    Neuronpedia

    INDEX
    Explanations

    Movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dice
    -0.07
     Öğren
    -0.06
     AST
    -0.06
     Prelude
    -0.06
    erge
    -0.06
    Nevertheless
    -0.06
    _static
    -0.06
     příst
    -0.06
     cannot
    -0.06
     tim
    -0.06
    POSITIVE LOGITS
     goats
    0.07
     vyvol
    0.07
     Χ
    0.06
    ones
    0.06
     seams
    0.06
    semb
    0.06
    .product
    0.06
    沖
    0.06
    aklı
    0.06
     καν
    0.06
    Act Density 0.031%

    No Known Activations