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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่งข
    -0.07
    'im
    -0.06
    TOCOL
    -0.06
    чного
    -0.06
    '*
    -0.06
     oluş
    -0.06
     sauces
    -0.06
    لل
    -0.06
    Роз
    -0.06
    عود
    -0.06
    POSITIVE LOGITS
    urchased
    0.07
     založ
    0.06
    ️
    0.06
     Expected
    0.06
     Explain
    0.06
     AtomicInteger
    0.06
    -I
    0.06
    	freopen
    0.06
    箱
    0.06
     macro
    0.06
    Act Density 0.004%

    No Known Activations