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

    Neuronpedia

    INDEX
    Explanations

    analysis and suitability for context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.48
    まり
    0.42
    カーテン
    0.41
    カ
    0.41
    <<
    0.41
    eras
    0.40
    णि
    0.40
    芒
    0.39
    ↵
    0.38
    ambient
    0.38
    POSITIVE LOGITS
     Prüfung
    0.52
    ূর্ন
    0.49
     das
    0.48
     ihr
    0.48
     McLeod
    0.48
     deshalb
    0.47
    সংখ্য
    0.47
     ബ്രിട്ട
    0.47
    ותר
    0.46
     schwier
    0.46
    Act Density 0.002%

    No Known Activations