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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	os
    -0.08
    Fig
    -0.07
    	for
    -0.07
     mg
    -0.07
    	open
    -0.07
    }><
    -0.07
    imer
    -0.07
     PubMed
    -0.06
    　
    -0.06
    64
    -0.06
    POSITIVE LOGITS
     تی
    0.07
     реб
    0.07
    bildung
    0.07
     Leben
    0.06
    leurs
    0.06
    先
    0.06
     QVERIFY
    0.06
     tup
    0.06
    aight
    0.06
    ‌کند
    0.06
    Act Density 0.016%

    No Known Activations