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

    Neuronpedia

    INDEX
    Explanations

    physically based, armor, countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tać
    0.48
    㝢
    0.47
     كات
    0.46
     منك
    0.46
    中共
    0.46
    ars
    0.45
    轮回
    0.45
    ujú
    0.44
     ք
    0.44
     materiál
    0.44
    POSITIVE LOGITS
    o
    0.55
    a
    0.52
    in
    0.50
    chance
    0.50
    act
    0.46
    houses
    0.45
    u
    0.45
     ширина
    0.44
    p
    0.44
    b
    0.44
    Act Density 0.000%

    No Known Activations