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

    Neuronpedia

    INDEX
    Explanations

    python code imports and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ומר
    0.44
    楦
    0.43
    悅
    0.40
     सुगंध
    0.40
     چشم
    0.40
    ClFN
    0.39
     кли
    0.38
    רט
    0.37
    ^{*}$,
    0.37
     оча
    0.37
    POSITIVE LOGITS
     Py
    0.88
    Py
    0.80
     Python
    0.80
     python
    0.78
    Python
    0.74
    PYTHON
    0.73
     py
    0.71
     built
    0.70
    built
    0.70
    pyx
    0.70
    Act Density 0.035%

    No Known Activations