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

    Neuronpedia

    INDEX
    Explanations

    confidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Saved
    -0.07
    TP
    -0.06
    owntown
    -0.06
    _TUN
    -0.06
     WP
    -0.06
     OBS
    -0.06
     configuration
    -0.06
    道
    -0.06
     override
    -0.06
     TMP
    -0.06
    POSITIVE LOGITS
    من
    0.07
    aData
    0.07
    σσότε
    0.07
    مدة
    0.07
     hacia
    0.06
     fluctuations
    0.06
    __)↵↵
    0.06
     plugged
    0.06
     Aleppo
    0.06
     behaving
    0.06
    Act Density 0.002%

    No Known Activations