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

    Neuronpedia

    INDEX
    Explanations

    think of it like this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    1.13
    ों
    1.12
    itam
    1.01
    a
    0.99
    ها
    0.98
     বিষয়টি
    0.96
    া
    0.96
     it
    0.95
     которого
    0.94
    selected
    0.93
    POSITIVE LOGITS
    self
    1.23
    inerary
    1.22
    zelf
    1.18
     all
    1.18
    ſelf
    1.15
    SELF
    1.08
    জ্জ
    1.05
     monet
    1.05
     próprios
    1.04
     happening
    1.03
    Act Density 0.216%

    No Known Activations