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

    Neuronpedia

    INDEX
    Explanations

    ambiguous wording

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bot
    -0.07
    Kim
    -0.07
     etabl
    -0.07
     Established
    -0.07
    >T
    -0.07
     提
    -0.07
     estabele
    -0.07
     establishes
    -0.07
     Kim
    -0.07
     vouloir
    -0.07
    POSITIVE LOGITS
     הראש
    0.11
     restantes
    0.10
     kollha
    0.10
     rehetra
    0.10
     الموجود
    0.09
     הזה
    0.08
     الوحيد
    0.08
     darn
    0.08
     الموجودة
    0.08
     الماضية
    0.08
    Act Density 0.064%

    No Known Activations