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

    Neuronpedia

    INDEX
    Explanations

    Borrowing concept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вист
    -0.08
     Luca
    -0.07
     iṣẹ
    -0.07
     waste
    -0.07
     روی
    -0.07
     TCHAR
    -0.07
     wun
    -0.07
    nię
    -0.07
     aqua
    -0.07
     doğ
    -0.07
    POSITIVE LOGITS
     имп
    0.08
    '',
    0.08
    သာ
    0.08
     правила
    0.08
     blockers
    0.08
     guarantees
    0.08
     безопасности
    0.08
     obey
    0.08
    ാദ
    0.08
     ограничения
    0.08
    Act Density 0.001%

    No Known Activations