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

    Neuronpedia

    INDEX
    Explanations

    list comprehensions and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distributing
    0.46
     tumours
    0.45
    梠
    0.40
     automating
    0.40
     producing
    0.39
    ôtels
    0.39
    āju
    0.39
     Producing
    0.39
     wirelessly
    0.38
     voluntarily
    0.38
    POSITIVE LOGITS
     encom
    0.48
    summary
    0.46
     குறித்து
    0.46
    obe
    0.45
     सुनने
    0.45
    id
    0.43
     antes
    0.43
     antecedentes
    0.43
    value
    0.42
     richt
    0.41
    Act Density 0.000%

    No Known Activations