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
    ционной
    -0.07
    优势
    -0.07
    iales
    -0.07
     Cunning
    -0.07
    .shows
    -0.06
    =y
    -0.06
    .ua
    -0.06
    τη
    -0.06
    SOLE
    -0.06
     треть
    -0.06
    POSITIVE LOGITS
     spheres
    0.07
     Becker
    0.06
     SimpleDateFormat
    0.06
    (SC
    0.06
    Await
    0.06
     Tyler
    0.06
     couple
    0.06
    вор
    0.06
     Suggestions
    0.05
     меропри
    0.05
    Act Density 0.002%

    No Known Activations