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

    Neuronpedia

    INDEX
    Explanations

    c# code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tathapi
    1.20
     دى
    1.13
    揊
    1.11
     ምንም
    1.11
    swadian
    1.10
    ্ী
    1.09
    맇
    1.09
     የተለያዩ
    1.08
     hermosa
    1.06
     gacche
    1.05
    POSITIVE LOGITS
     diving
    0.72
     express
    0.69
     freed
    0.67
     v
    0.67
     had
    0.67
    boat
    0.66
     as
    0.66
     dive
    0.65
     due
    0.64
     because
    0.64
    Act Density 0.005%

    No Known Activations