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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    窭
    -0.07
    (hwnd
    -0.07
     Önceki
    -0.07
     TKey
    -0.07
    wnd
    -0.07
    UCE
    -0.07
    /train
    -0.07
     Quotes
    -0.07
     punching
    -0.07
    ,'%
    -0.06
    POSITIVE LOGITS
    聊城
    0.07
    cidade
    0.07
     Rossi
    0.07
     наблюда
    0.07
    SYS
    0.07
     Advanced
    0.07
    cities
    0.06
     composite
    0.06
     bình
    0.06
     dalla
    0.06
    Act Density 0.044%

    No Known Activations