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

    Neuronpedia

    INDEX
    Explanations

    protocol, protocol, program, protocol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ूज
    0.39
    cius
    0.39
    Prior
    0.39
    海道
    0.39
     wcześ
    0.38
     الكامل
    0.38
    事前
    0.38
    kje
    0.37
    ekw
    0.37
     ৭৮
    0.36
    POSITIVE LOGITS
     up
    0.41
     glad
    0.41
     drauf
    0.40
     Margaret
    0.40
     প্রজন্মের
    0.39
     Up
    0.39
    บน
    0.38
     Slowly
    0.38
     nejen
    0.37
     오늘도
    0.37
    Act Density 0.004%

    No Known Activations