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

    Neuronpedia

    INDEX
    Explanations

    Health and avoidance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hist
    -0.07
     Notes
    -0.07
    ros
    -0.06
     wavelength
    -0.06
     як
    -0.06
    """
↵
    -0.06
    Notes
    -0.06
     briefing
    -0.06
     Where
    -0.06
     asynchronously
    -0.06
    POSITIVE LOGITS
     rivals
    0.06
    liğin
    0.06
     desea
    0.06
    ="'
    0.06
    vidia
    0.06
     akıl
    0.06
    .nil
    0.06
    /cgi
    0.06
     dokon
    0.06
    (bits
    0.06
    Act Density 0.019%

    No Known Activations