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

    Neuronpedia

    INDEX
    Explanations

    Foundation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fully
    -0.08
    allen
    -0.08
    Son
    -0.07
    یش
    -0.07
    /utils
    -0.07
     Střed
    -0.07
    _DEFINE
    -0.07
    ày
    -0.07
     Vest
    -0.06
     slowly
    -0.06
    POSITIVE LOGITS
    act
    0.06
    Hor
    0.06
    })"↵
    0.06
     miscon
    0.06
     امتی
    0.06
    �单
    0.06
    sig
    0.06
    써
    0.06
    Smart
    0.06
     NXT
    0.06
    Act Density 0.006%

    No Known Activations