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

    Neuronpedia

    INDEX
    Explanations

    Acknowledgments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undercover
    -0.08
     kun
    -0.08
     Height
    -0.08
     anabolic
    -0.07
    átil
    -0.07
     armored
    -0.07
     height
    -0.07
     grilled
    -0.07
     agenda
    -0.07
    穿
    -0.07
    POSITIVE LOGITS
     thanking
    0.13
    感谢
    0.13
    cimientos
    0.12
     gratitude
    0.12
     remerc
    0.11
     heartfelt
    0.10
     acknowled
    0.10
     thanked
    0.10
     agrade
    0.10
     agradecer
    0.10
    Act Density 0.013%

    No Known Activations