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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.48
    не
    0.44
    и
    0.42
    хо
    0.42
    же
    0.41
     .
    0.41
    вт
    0.41
    бок
    0.41
    дон
    0.40
    он
    0.40
    POSITIVE LOGITS
     Misalnya
    0.46
     هسه
    0.45
     उदाहरण
    0.45
    ❉
    0.44
     Library
    0.43
     예를
    0.43
     Sampling
    0.43
     Rhino
    0.42
     Watershed
    0.42
     Score
    0.42
    Act Density 0.001%

    No Known Activations