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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Link
    -0.07
    射
    -0.06
     Ευ
    -0.06
     III
    -0.06
     напря
    -0.06
    -East
    -0.06
     Weston
    -0.06
    iêng
    -0.06
     (*.
    -0.06
    Neo
    -0.06
    POSITIVE LOGITS
     bg
    0.07
    GENCY
    0.07
     ),↵
    0.07
    acho
    0.07
     dogs
    0.07
    ),↵↵
    0.06
    )?↵
    0.06
    _));↵
    0.06
    ..."↵
    0.06
    LCD
    0.06
    Act Density 0.262%

    No Known Activations