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

    Neuronpedia

    INDEX
    Explanations

    door

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    青
    -0.08
    (net
    -0.08
    提倡
    -0.07
     accusations
    -0.07
     inches
    -0.07
    "P
    -0.07
     investment
    -0.07
    (F
    -0.07
    lyn
    -0.07
     projections
    -0.07
    POSITIVE LOGITS
     door
    0.09
    odu
    0.07
    门
    0.07
    checks
    0.07
    ethod
    0.07
    bole
    0.07
    倒霉
    0.07
    //!
    0.07
    ılı
    0.07
     Instruments
    0.07
    Act Density 0.014%

    No Known Activations