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

    Neuronpedia

    INDEX
    Explanations

    take up space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     considerate
    0.45
     pirates
    0.42
     considér
    0.40
     spares
    0.40
    បំ
    0.39
     pirate
    0.39
    pir
    0.38
     considered
    0.37
     ব্যবস্থা
    0.37
    考虑
    0.37
    POSITIVE LOGITS
     up
    0.69
    ขึ้น
    0.54
     lên
    0.51
     place
    0.46
    形
    0.45
     Up
    0.44
     Examination
    0.43
    up
    0.42
     Счет
    0.42
     Thế
    0.42
    Act Density 0.005%

    No Known Activations