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

    Neuronpedia

    INDEX
    Explanations

    Write

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ូវ
    0.52
    দ্ভ
    0.52
    ارض
    0.50
    ждествен
    0.49
    мая
    0.47
     അയാള
    0.46
     Nahr
    0.46
     dieta
    0.46
    Woh
    0.46
    దేశ
    0.45
    POSITIVE LOGITS
     python
    0.91
     Python
    0.88
    python
    0.85
     down
    0.83
    Python
    0.78
     Java
    0.66
     PYTHON
    0.66
     JavaScript
    0.63
     up
    0.61
    PYTHON
    0.61
    Act Density 0.154%

    No Known Activations