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

    Neuronpedia

    INDEX
    Explanations

    vector databases and embeddings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    时
    0.59
    ה
    0.54
    数
    0.54
     zum
    0.52
     firstName
    0.52
     bahasa
    0.51
     نتيجة
    0.51
    allOf
    0.50
     sozial
    0.50
     sytu
    0.50
    POSITIVE LOGITS
    िया
    0.59
     enablement
    0.52
    rail
    0.51
     Carrick
    0.51
     Rail
    0.49
     ज्वेल
    0.49
    ገልግሎ
    0.48
    ystone
    0.48
    ಮೇ
    0.48
     نکن
    0.48
    Act Density 0.013%

    No Known Activations