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

    Neuronpedia

    INDEX
    Explanations

    changing colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'n
    -0.06
    /tutorial
    -0.06
    -toggle
    -0.06
    151
    -0.06
    estival
    -0.06
    /.
    -0.06
     流
    -0.06
    ifica
    -0.06
    μμα
    -0.06
    文
    -0.06
    POSITIVE LOGITS
    ultureInfo
    0.07
     Netherlands
    0.06
     actionable
    0.06
     UFC
    0.06
    ，此
    0.06
     Doors
    0.06
     POSS
    0.06
     """
↵
    0.06
     Tiffany
    0.06
    """
↵
↵
    0.06
    Act Density 0.013%

    No Known Activations