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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rus
    -0.07
     فوت
    -0.06
     repaired
    -0.06
    cribed
    -0.06
    wner
    -0.06
     streak
    -0.06
     detay
    -0.06
     जनवर
    -0.06
    困
    -0.06
     populous
    -0.06
    POSITIVE LOGITS
    ỗ
    0.07
    orderby
    0.06
    AGES
    0.06
    #ifdef
    0.06
     กำ
    0.06
    λίου
    0.06
    чает
    0.06
    	tc
    0.06
     Archae
    0.06
    کنان
    0.06
    Act Density 0.012%

    No Known Activations