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

    Neuronpedia

    INDEX
    Explanations

    confinement to home/room

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Princeton
    -0.06
    ้าหน
    -0.06
    precedented
    -0.06
     defended
    -0.06
    奖
    -0.06
    Ma
    -0.05
     пи
    -0.05
    杉
    -0.05
     neighbourhood
    -0.05
    ули
    -0.05
    POSITIVE LOGITS
    /ip
    0.08
    .LayoutControlItem
    0.07
    _A
    0.07
    ią
    0.06
    /close
    0.06
     '..
    0.06
    ζει
    0.06
    indrome
    0.06
    burg
    0.06
    forcing
    0.06
    Act Density 0.029%

    No Known Activations