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

    Neuronpedia

    INDEX
    Explanations

    key improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Blues
    0.40
    Ru
    0.38
    Tar
    0.38
    Blu
    0.36
    tow
    0.36
    紫外線
    0.35
    blues
    0.34
    氮
    0.34
     Ding
    0.34
    并发
    0.34
    POSITIVE LOGITS
     Mel
    0.41
     ਦ
    0.40
     MEL
    0.38
     DEL
    0.36
     میر
    0.36
     المتحدة
    0.36
     mel
    0.35
     disconnect
    0.35
     دى
    0.35
     लड़के
    0.35
    Act Density 0.027%

    No Known Activations