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
     decomposition
    -0.07
     giờ
    -0.07
    histor
    -0.07
    ponsible
    -0.07
    єте
    -0.06
    formed
    -0.06
    助
    -0.06
    店
    -0.06
     şehir
    -0.06
     людини
    -0.06
    POSITIVE LOGITS
     XPAR
    0.06
    �
    0.06
     istih
    0.06
    htm
    0.06
    0.06
    _EXPECT
    0.06
     HAL
    0.06
    Wil
    0.06
     Maced
    0.06
     프
    0.06
    Act Density 0.004%

    No Known Activations