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

    Neuronpedia

    INDEX
    Explanations

    "What is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يع
    0.54
     fillets
    0.54
    ，
    0.54
     föl
    0.53
    //
    0.52
    âni
    0.52
     enqu
    0.51
     gelegen
    0.51
    el
    0.50
     substrings
    0.49
    POSITIVE LOGITS
    ak
    0.54
     watchdog
    0.54
     באמצעות
    0.53
     किड्स
    0.53
    ۲
    0.53
     Health
    0.52
     Фонбет
    0.52
     தீவிர
    0.52
     দিচ্ছেন
    0.50
     જાહેર
    0.50
    Act Density 0.310%

    No Known Activations