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

    Neuronpedia

    INDEX
    Explanations

    facilitate commissioning and building performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nurt
    0.45
     irrig
    0.44
     diversos
    0.42
    ব্র
    0.42
     dispoz
    0.42
    urea
    0.41
     intramuscular
    0.41
     setempat
    0.41
    in
    0.41
     dioxide
    0.40
    POSITIVE LOGITS
     אם
    0.56
     பிறகு
    0.55
     있다면
    0.53
     измени
    0.52
    แล้ว
    0.51
     सफल
    0.51
    我们
    0.50
    结局
    0.50
    ถ้า
    0.49
     після
    0.49
    Act Density 0.024%

    No Known Activations