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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives for nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    铒
    0.39
     Sereth
    0.38
     convexo
    0.36
     pInBuffer
    0.36
     Фурга
    0.34
    Aslamualaikum
    0.34
     mannit
    0.33
     Süden
    0.33
     челу
    0.33
    rbrakk
    0.33
    POSITIVE LOGITS
    ↵
    0.39
    ‌
    0.38
    <eos>
    0.36
     ‎
    0.35
          
    0.34
      
    0.34
    <0xC2>
    0.34
     ​​
    0.33
    <0xE2>
    0.33
    <start_of_image>
    0.33
    Act Density 0.161%

    No Known Activations