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

    Neuronpedia

    INDEX
    Explanations

    acronyms and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    फ़
    0.36
    (“
    0.35
    𝑠
    0.34
    Craw
    0.33
    Summary
    0.33
    String
    0.33
     फूलों
    0.33
    SUMMARY
    0.31
    Har
    0.31
    চী
    0.31
    POSITIVE LOGITS
     debacle
    0.32
     batsmen
    0.32
    zens
    0.30
     있던
    0.30
     ballad
    0.29
     stessi
    0.29
     Libertadores
    0.29
     veracity
    0.28
     Puja
    0.28
     justement
    0.28
    Act Density 0.056%

    No Known Activations