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
    の
    -0.08
    	names
    -0.06
     vocabulary
    -0.06
    語
    -0.06
    curso
    -0.06
    SEMB
    -0.06
     нових
    -0.06
    	ctrl
    -0.06
    quet
    -0.06
    че
    -0.06
    POSITIVE LOGITS
    tplib
    0.06
    BN
    0.06
     LatLng
    0.06
     кв
    0.06
    ूबर
    0.06
     Mayweather
    0.06
     Shotgun
    0.06
     Cyan
    0.06
    Prefs
    0.06
     onFinish
    0.06
    Act Density 0.000%

    No Known Activations