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

    Neuronpedia

    INDEX
    Explanations

    lost track of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    станти
    0.46
     somet
    0.46
    지
    0.45
     draught
    0.45
     ხელისუფ
    0.45
    ခန်း
    0.44
    cakes
    0.44
    してください
    0.44
     транспорт
    0.44
     probing
    0.44
    POSITIVE LOGITS
    Alloc
    0.57
    Lu
    0.55
    Histogram
    0.51
    Lors
    0.51
    Lus
    0.50
    खे
    0.49
    "
    0.48
     Juel
    0.47
    8
    0.46
    Vi
    0.46
    Act Density 0.000%

    No Known Activations