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

    Neuronpedia

    INDEX
    Explanations

    Python programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    міст
    0.41
     charset
    0.41
     ghosts
    0.38
     names
    0.38
     annotation
    0.37
    Cleanup
    0.37
     cleaning
    0.37
     Cleanup
    0.36
     scans
    0.36
     annotations
    0.36
    POSITIVE LOGITS
     Python
    0.49
    Python
    0.48
    Programming
    0.39
     विषम
    0.39
     Yue
    0.38
     Yav
    0.38
    python
    0.37
     ടീ
    0.37
    ℍ
    0.37
     Schrö
    0.37
    Act Density 0.000%

    No Known Activations