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

    Neuronpedia

    INDEX
    Explanations

    patterns in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Читати
    0.49
    Є
    0.45
     Casting
    0.45
    <start_of_image>
    0.44
    main
    0.41
    Би
    0.41
    ła
    0.40
    лось
    0.40
    arked
    0.40
    čný
    0.40
    POSITIVE LOGITS
     quell
    0.50
     Verfü
    0.47
     herunter
    0.46
     marry
    0.46
     விஷ
    0.46
    新技术
    0.46
     खोले
    0.46
     neuer
    0.46
    otong
    0.46
     hick
    0.46
    Act Density 0.016%

    No Known Activations