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

    Neuronpedia

    INDEX
    Explanations

    tiling suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (txt
    -0.07
    Producto
    -0.07
    prefix
    -0.06
    severity
    -0.06
    igits
    -0.06
    ujících
    -0.06
    uni
    -0.06
    oses
    -0.06
    boBox
    -0.06
    ujícím
    -0.06
    POSITIVE LOGITS
    .Abstract
    0.07
     дек
    0.06
    -dist
    0.06
    ımın
    0.06
     Hir
    0.06
     destruct
    0.06
    öff
    0.06
    #SBATCH
    0.06
    ์เซ
    0.06
    まだ
    0.06
    Act Density 0.004%

    No Known Activations