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

    Neuronpedia

    INDEX
    Explanations

    learning resources and tutorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    НЫ
    0.55
     ফ্লাইট
    0.54
     অব্যাহত
    0.50
     BlueprintName
    0.50
     설립
    0.49
     ውጤ
    0.48
    פ
    0.47
     નવી
    0.46
    実装
    0.46
    ഘടന
    0.46
    POSITIVE LOGITS
     small
    0.49
     same
    0.47
     elet
    0.46
     gambar
    0.46
     eco
    0.46
     web
    0.45
     wide
    0.45
     sporty
    0.44
     on
    0.43
     series
    0.43
    Act Density 0.003%

    No Known Activations