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

    Neuronpedia

    INDEX
    Explanations

    politicians

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detecting
    -0.07
    _amp
    -0.06
    itant
    -0.06
     reunion
    -0.06
     threatened
    -0.06
    ителем
    -0.06
     declar
    -0.06
     prob
    -0.06
    уч
    -0.06
     traps
    -0.06
    POSITIVE LOGITS
    ]]></
    0.08
    .fc
    0.07
    (DBG
    0.07
     Shooter
    0.07
    (details
    0.07
    ucken
    0.06
    基础
    0.06
     QLatin
    0.06
    ]=$
    0.06
     GDK
    0.06
    Act Density 0.011%

    No Known Activations