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

    Neuronpedia

    INDEX
    Explanations

    automating and optimizing processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    text
    0.50
    cro
    0.47
    sizing
    0.46
    urup
    0.46
     Cove
    0.45
     فرن
    0.45
    cooking
    0.45
     உத
    0.44
     carp
    0.44
    sphere
    0.43
    POSITIVE LOGITS
    خت
    0.50
     penyel
    0.46
     getUsersBy
    0.44
    나
    0.44
    ouche
    0.42
     shoved
    0.42
     diante
    0.41
    骶
    0.41
    娜
    0.40
     optimal
    0.40
    Act Density 0.001%

    No Known Activations