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

    Neuronpedia

    INDEX
    Explanations

    price risk derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     গঠন
    0.48
    t
    0.46
    coded
    0.46
    lands
    0.45
    rea
    0.44
    direction
    0.43
    crud
    0.43
    centroid
    0.43
    me
    0.42
    lan
    0.42
    POSITIVE LOGITS
     手
    0.54
     സിനിമ
    0.50
     célébr
    0.48
    Modifiers
    0.48
     Filme
    0.48
    㷫
    0.47
    幄
    0.47
    ىرى
    0.46
     américains
    0.46
     pleased
    0.46
    Act Density 0.004%

    No Known Activations