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

    Neuronpedia

    INDEX
    Explanations

    examples and categorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kultur
    0.42
     prestations
    0.42
     patrim
    0.41
     zdol
    0.41
     bezpiecze
    0.40
     feedwater
    0.39
     kalite
    0.39
     taff
    0.39
     ماشینونو
    0.38
     kvalitet
    0.38
    POSITIVE LOGITS
     downloadable
    0.71
     онлайн
    0.59
     Examples
    0.55
     YouTube
    0.54
     URLs
    0.54
     downloaded
    0.53
    具体
    0.53
     downloading
    0.52
     উদাহরণ
    0.52
     具体
    0.52
    Act Density 0.391%

    No Known Activations