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

    Neuronpedia

    INDEX
    Explanations

    Rule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dirs
    -0.07
     �
    -0.07
    活
    -0.07
     ص
    -0.07
    =db
    -0.07
     �
    -0.06
     Sav
    -0.06
     تنظیم
    -0.06
    境
    -0.06
    (ctx
    -0.06
    POSITIVE LOGITS
    Rule
    0.08
    _Common
    0.07
     TYPO
    0.07
    /styles
    0.06
    Dragon
    0.06
    Prod
    0.06
    -major
    0.06
    Rules
    0.06
     multipart
    0.06
     Major
    0.06
    Act Density 0.013%

    No Known Activations