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

    Neuronpedia

    INDEX
    Explanations

    _layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     segundos
    -0.07
    (descriptor
    -0.07
    ‿
    -0.07
     précis
    -0.07
     efect
    -0.07
    phies
    -0.07
     admission
    -0.07
    椀
    -0.07
     Yad
    -0.07
    ỉ
    -0.07
    POSITIVE LOGITS
    系列产品
    0.08
     İki
    0.07
    자의
    0.07
     ness
    0.07
     mqtt
    0.07
     backstory
    0.07
    势力
    0.07
     מבלי
    0.07
     BBB
    0.07
    车库
    0.07
    Act Density 0.001%

    No Known Activations