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

    Neuronpedia

    INDEX
    Explanations

    words regarding regrets or Spanish texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Everyone
    0.51
     B
    0.46
     l
    0.46
    อร์
    0.44
    j
    0.43
     YouTube
    0.43
     Remember
    0.42
     Dream
    0.42
      
    0.41
     You
    0.41
    POSITIVE LOGITS
    部件
    0.52
    🕎
    0.50
     покер
    0.50
     செறிவு
    0.50
     относя
    0.49
    häuse
    0.48
    ुसार
    0.46
    筮
    0.46
    🚱
    0.46
    ARTER
    0.46
    Act Density 0.007%

    No Known Activations