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

    Neuronpedia

    INDEX
    Explanations

    describing states or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perfetto
    0.40
    ঘ্রই
    0.40
     moyenne
    0.38
    യിലെ
    0.38
     Ony
    0.37
     equipments
    0.37
     নামটি
    0.37
    ത്തുന്ന
    0.36
     postérieures
    0.36
     നടക്കുന്ന
    0.36
    POSITIVE LOGITS
    ्ता
    0.39
    вах
    0.37
     ક્લિક
    0.36
     обстоя
    0.36
    сия
    0.36
     कहा
    0.35
    ма
    0.35
    ва
    0.34
    ṣ
    0.34
    。「
    0.33
    Act Density 0.164%

    No Known Activations