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
    Our
    -0.07
    ух
    -0.07
     Mil
    -0.06
     emulator
    -0.06
    .dir
    -0.06
     testimon
    -0.06
    .testng
    -0.06
     этого
    -0.06
    بع
    -0.06
     Hol
    -0.06
    POSITIVE LOGITS
    ValuePair
    0.07
    .repositories
    0.06
    .getColor
    0.06
    алась
    0.06
     şer
    0.06
    韓
    0.06
    илась
    0.06
     Alexandria
    0.06
    .Socket
    0.06
    ịp
    0.06
    Act Density 0.040%

    No Known Activations