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

    Neuronpedia

    INDEX
    Explanations

    episode or episode-like content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一带
    0.45
    ূর্ন
    0.43
    gina
    0.42
    ราช
    0.41
    নের
    0.41
    Conservation
    0.40
     ปุ่ม
    0.39
     currentLocation
    0.39
    柰
    0.39
    чина
    0.38
    POSITIVE LOGITS
     w
    0.47
     gap
    0.41
     wt
    0.39
     fim
    0.38
     episode
    0.38
     episodes
    0.38
     Gap
    0.38
     mpg
    0.38
     Generally
    0.38
     Re
    0.37
    Act Density 0.000%

    No Known Activations