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

    Neuronpedia

    INDEX
    Explanations

    articles, auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     safezone
    -0.08
    (BuildContext
    -0.07
     domingo
    -0.07
     exiting
    -0.07
    iring
    -0.06
    utto
    -0.06
    系
    -0.06
     παρ
    -0.06
    ](↵
    -0.06
     thumbnail
    -0.06
    POSITIVE LOGITS
     sadece
    0.07
    reten
    0.07
    ‌ی
    0.06
    ，上
    0.06
    arently
    0.06
    Für
    0.06
     العراق
    0.06
     مطرح
    0.06
    ่ใช
    0.06
    -widget
    0.06
    Act Density 0.170%

    No Known Activations