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

    Neuronpedia

    INDEX
    Explanations

    could

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pancakes
    -0.07
     speak
    -0.07
    entin
    -0.07
    "x
    -0.07
     meets
    -0.07
     enquiries
    -0.07
    ottenham
    -0.07
    パーティー
    -0.07
     counterparts
    -0.07
    我个人
    -0.07
    POSITIVE LOGITS
    ıld
    0.07
    地球
    0.06
     układ
    0.06
    WSC
    0.06
     surplus
    0.06
    生態
    0.06
     HOLDER
    0.06
    ﺩ
    0.06
     угол
    0.06
    сад
    0.06
    Act Density 0.033%

    No Known Activations