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

    Neuronpedia

    INDEX
    Explanations

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असलेल्या
    0.28
    chränk
    0.27
    larını
    0.27
     അതിനാ
    0.27
     অদ্ভুত
    0.26
     Hadoop
    0.26
     শতকরা
    0.26
     தண்ணீ
    0.26
    យើង
    0.25
    妷
    0.25
    POSITIVE LOGITS
    ↵
    0.34
    .
    0.33
    ↵↵
    0.26
    ,
    0.25
    ;
    0.24
     commence
    0.20
     uspe
    0.20
    u
    0.20
    +.
    0.19
    5
    0.19
    Act Density 0.023%

    No Known Activations