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

    Neuronpedia

    INDEX
    Explanations

    shapes and forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سٹی
    0.43
     سابقا
    0.42
     ښ
    0.42
     deseja
    0.41
     খন
    0.41
    وسف
    0.40
    ايبي
    0.40
    off
    0.40
    uchi
    0.40
    everyone
    0.40
    POSITIVE LOGITS
    Payments
    0.40
     work
    0.40
     Shapes
    0.40
    Shapes
    0.39
     compare
    0.39
     shape
    0.39
    Lower
    0.38
     Shape
    0.37
    Birthday
    0.37
    LowerCase
    0.36
    Act Density 0.000%

    No Known Activations