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

    Neuronpedia

    INDEX
    Explanations

    dis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ic
    -0.07
    inem
    -0.07
    ustry
    -0.07
    ível
    -0.07
     CLOSED
    -0.07
     mev
    -0.07
    ewed
    -0.07
     Meadows
    -0.07
    έλ
    -0.06
    	v
    -0.06
    POSITIVE LOGITS
    Connection
    0.06
    Gear
    0.06
     rocket
    0.06
     verb
    0.06
    282
    0.06
     разработ
    0.06
    .sub
    0.05
    }",
    0.05
    <Value
    0.05
     رابط
    0.05
    Act Density 0.002%

    No Known Activations