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

    Neuronpedia

    INDEX
    Explanations

    Recipes and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mail
    -0.07
     Sharia
    -0.06
     bureaucrats
    -0.06
    決
    -0.06
    _cod
    -0.06
     Officials
    -0.06
     xin
    -0.06
    左
    -0.06
     guru
    -0.06
    ああ
    -0.06
    POSITIVE LOGITS
    Linux
    0.06
     repealed
    0.06
     (=
    0.06
     foss
    0.06
    brities
    0.06
     Orden
    0.06
    .jpg
    0.06
    --
    0.06
     желуд
    0.06
    .pdf
    0.06
    Act Density 0.003%

    No Known Activations