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

    Neuronpedia

    INDEX
    Explanations

    room

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fri
    -0.07
    embali
    -0.07
    Mich
    -0.07
     bedrooms
    -0.06
    powered
    -0.06
     Mich
    -0.06
     arrivals
    -0.06
    víc
    -0.06
    いる
    -0.06
    用户名
    -0.06
    POSITIVE LOGITS
     srov
    0.07
     stamina
    0.07
     "'"
    0.07
     \"{
    0.07
     Gemini
    0.07
     Châu
    0.06
     Benghazi
    0.06
     Doe
    0.06
     narr
    0.06
    'C
    0.06
    Act Density 0.066%

    No Known Activations