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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marshal
    -0.07
     Earn
    -0.07
    تاح
    -0.07
    盗
    -0.07
     då
    -0.06
    \Abstract
    -0.06
    𝗻
    -0.06
    (relative
    -0.06
    灯具
    -0.06
    تأمين
    -0.06
    POSITIVE LOGITS
    ᡌ
    0.07
     trif
    0.07
    StyleSheet
    0.07
    工业园
    0.07
     slik
    0.06
    Pages
    0.06
    宗旨
    0.06
     Влад
    0.06
     Pussy
    0.06
     משום
    0.06
    Act Density 0.002%

    No Known Activations