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

    Neuronpedia

    INDEX
    Explanations

    base case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISTRIBUT
    -0.07
     coordination
    -0.07
     viewHolder
    -0.07
    lica
    -0.07
     обнаруж
    -0.07
     uğ
    -0.07
    	min
    -0.06
     referral
    -0.06
    	reader
    -0.06
    Occ
    -0.06
    POSITIVE LOGITS
     السعودية
    0.07
    ми
    0.06
     centralized
    0.06
     δύο
    0.06
     《
    0.06
    sahuje
    0.06
    akukan
    0.06
    Building
    0.06
    ールド
    0.06
    鲁
    0.06
    Act Density 0.006%

    No Known Activations