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

    Neuronpedia

    INDEX
    Explanations

    Specifically

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _aliases
    -0.07
     ز
    -0.06
     وجود
    -0.06
     rises
    -0.06
     багато
    -0.06
     appe
    -0.06
     tersebut
    -0.06
     universities
    -0.06
     licences
    -0.06
     ورد
    -0.06
    POSITIVE LOGITS
     Specifically
    0.07
     ------------------------------------------------------------------------↵
    0.06
     değildi
    0.06
    _SAMPLES
    0.06
     GG
    0.06
     specifically
    0.06
     dřev
    0.06
    ]:↵↵
    0.06
     Drake
    0.06
     Вік
    0.06
    Act Density 0.017%

    No Known Activations