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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    炊
    -0.08
     Converter
    -0.08
     daytime
    -0.08
    aycast
    -0.07
    뤗
    -0.07
    earn
    -0.07
    шение
    -0.07
    inkle
    -0.07
    enever
    -0.07
    _steps
    -0.07
    POSITIVE LOGITS
     Dee
    0.08
    下面是小
    0.07
    ')</
    0.07
     tại
    0.07
     Pad
    0.07
    individual
    0.07
     bąd
    0.07
    പ
    0.07
    —he
    0.07
    永
    0.07
    Act Density 0.027%

    No Known Activations