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

    Neuronpedia

    INDEX
    Explanations

    describing what images show

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utiliser
    0.51
     использовать
    0.43
    این
    0.41
    ลา
    0.39
    柅
    0.39
    quetas
    0.39
    inas
    0.39
    ekom
    0.39
     incluye
    0.38
    omez
    0.38
    POSITIVE LOGITS
     actuation
    0.42
     ;{
    0.39
     titled
    0.39
     mat
    0.38
     lotta
    0.37
     goes
    0.37
     গেছে
    0.36
     looping
    0.36
     GO
    0.35
     olduğunu
    0.35
    Act Density 0.001%

    No Known Activations