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

    Neuronpedia

    INDEX
    Explanations

    mathematical or natural language context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਕਿ
    0.48
     nationalist
    0.47
     riforma
    0.46
    াহিয়ার
    0.42
     بابەت
    0.42
     tratt
    0.42
    жным
    0.42
    প্রে
    0.42
     vzděl
    0.42
    িতেছিল
    0.41
    POSITIVE LOGITS
    ul
    0.54
    ti
    0.49
    O
    0.49
    hav
    0.48
    ten
    0.47
    sworth
    0.47
    tons
    0.47
    sniffer
    0.46
    site
    0.46
    winner
    0.46
    Act Density 0.002%

    No Known Activations