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

    Neuronpedia

    INDEX
    Explanations

    ).

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    admins
    -0.07
     tand
    -0.07
    اب
    -0.06
    _REPLACE
    -0.06
     decryption
    -0.06
     فاصله
    -0.06
    ้ใน
    -0.06
    +r
    -0.06
    peror
    -0.06
    extra
    -0.06
    POSITIVE LOGITS
    	assertEquals
    0.06
     ор
    0.06
     ngăn
    0.06
    ，不
    0.06
     žádné
    0.06
    exter
    0.06
     Sonuç
    0.06
     #=>
    0.06
     Posts
    0.06
    iej
    0.06
    Act Density 0.109%

    No Known Activations