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

    Neuronpedia

    INDEX
    Explanations

    quantifiable achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theoretical
    0.53
    σίας
    0.48
     apprendre
    0.48
     learn
    0.46
     나오는
    0.45
     idéal
    0.45
    原则
    0.44
     будет
    0.44
     Theoretical
    0.44
     सुनना
    0.42
    POSITIVE LOGITS
     collaborated
    0.61
     pioneered
    0.53
    Implemented
    0.53
     बचाया
    0.52
     participaron
    0.50
    launched
    0.50
    Increased
    0.49
    replaced
    0.49
     Launched
    0.48
    推出了
    0.47
    Act Density 0.016%

    No Known Activations