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

    Neuronpedia

    INDEX
    Explanations

    when specific date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रसन्न
    0.61
     thankful
    0.59
     تست
    0.58
     provoke
    0.57
     thả
    0.56
    STRUCTIONS
    0.56
     selama
    0.55
     उत्साहित
    0.55
     ನನ್ನ
    0.55
     দিয়েছেন
    0.55
    POSITIVE LOGITS
     inception
    0.62
     існу
    0.59
    介入
    0.58
     pojav
    0.55
     it
    0.54
     emergence
    0.54
    esistenza
    0.53
     APPE
    0.52
     commenced
    0.51
     existed
    0.50
    Act Density 0.086%

    No Known Activations