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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𐤕
    -0.07
    ↝
    -0.07
     nod
    -0.06
     siden
    -0.06
    扣
    -0.06
    不存在
    -0.06
    榄
    -0.06
    ﺉ
    -0.06
    剐
    -0.06
    delta
    -0.06
    POSITIVE LOGITS
     Commercial
    0.07
     exterior
    0.07
    大全
    0.07
     utilisé
    0.07
     của
    0.07
    กลาง
    0.07
     unconventional
    0.07
    しまう
    0.07
    uble
    0.06
    電子郵件
    0.06
    Act Density 0.001%

    No Known Activations