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
    _DP
    -0.08
    ":↵↵
    -0.07
    /ar
    -0.07
    tile
    -0.06
    /world
    -0.06
    rello
    -0.06
    átis
    -0.06
     franç
    -0.06
     Μη
    -0.06
    _ports
    -0.06
    POSITIVE LOGITS
     """
    0.13
    """
    0.10
    0.07
    ="""
    0.07
    及
    0.07
    ("""
    0.07
    0.07
    ichever
    0.07
    deprecated
    0.07
     comprising
    0.06
    Act Density 0.001%

    No Known Activations