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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GW
    -0.07
    —one
    -0.06
     Brooklyn
    -0.06
    _Group
    -0.06
     how
    -0.06
    ्रमण
    -0.06
    /reset
    -0.06
    screens
    -0.06
    -multi
    -0.06
    上海
    -0.06
    POSITIVE LOGITS
    Disappear
    0.06
    prit
    0.06
     国产
    0.06
    Š
    0.06
    跑
    0.06
    Beta
    0.06
     Beef
    0.06
    伍
    0.06
    PRESENT
    0.06
     Rahul
    0.06
    Act Density 0.094%

    No Known Activations