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

    Neuronpedia

    INDEX
    Explanations

    distributed computing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fred
    -0.07
     被
    -0.07
     misinformation
    -0.07
    เอ
    -0.06
     تصو
    -0.06
    telegram
    -0.06
    	ep
    -0.06
     masturb
    -0.06
    LatLng
    -0.06
     教
    -0.06
    POSITIVE LOGITS
     setback
    0.07
     /↵
    0.07
     Aleppo
    0.07
    	stats
    0.07
     <$
    0.06
    esin
    0.06
     Inn
    0.06
    _INET
    0.06
    asser
    0.06
    );
    0.06
    Act Density 0.015%

    No Known Activations