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
    Pot
    -0.07
     grim
    -0.06
    irth
    -0.06
    &a
    -0.06
     přece
    -0.06
     Magnet
    -0.06
    GameState
    -0.06
    思考
    -0.06
     mục
    -0.06
    地区
    -0.06
    POSITIVE LOGITS
     Possible
    0.06
    (point
    0.06
    (txt
    0.06
    妹
    0.06
     algae
    0.06
     ESA
    0.06
     Kind
    0.06
     stmt
    0.06
     گزارش
    0.06
    aggregate
    0.06
    Act Density 0.000%

    No Known Activations