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

    Neuronpedia

    INDEX
    Explanations

    main method in Java

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    皮
    0.80
    并购
    0.76
    وَ
    0.74
    🥭
    0.73
     función
    0.73
     الد
    0.72
     বন্দরের
    0.72
    Har
    0.72
     מק
    0.72
     menu
    0.72
    POSITIVE LOGITS
    BufferedReader
    0.76
     PrintWriter
    0.69
    లేదు
    0.66
    BufferedWriter
    0.65
    sein
    0.64
     BufferedReader
    0.64
    不受
    0.64
    andidate
    0.62
    throws
    0.62
     TextField
    0.61
    Act Density 0.001%

    No Known Activations