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

    Neuronpedia

    INDEX
    Explanations

    Python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indexBuffer
    0.47
     marginRight
    0.46
    ەڕ
    0.45
    สะ
    0.44
    featuresMatrix
    0.44
     સંપૂર્ણ
    0.41
     numberOfRows
    0.40
    腴
    0.40
     लक्ष
    0.39
    ून्य
    0.39
    POSITIVE LOGITS
     None
    1.00
    None
    1.00
     isinstance
    0.94
     asyncio
    0.87
    pygame
    0.86
    getattr
    0.84
     hashlib
    0.82
     getattr
    0.81
    str
    0.80
    np
    0.80
    Act Density 0.195%

    No Known Activations