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

    Neuronpedia

    INDEX
    Explanations

    additional ceremonies, inflation eased, class honours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মাননীয়
    0.54
    (!)
    0.49
     २०२
    0.47
    竟然
    0.46
     मटेरियल
    0.46
     যাইতে
    0.46
    居然
    0.45
    宣传
    0.44
    सुद्धा
    0.43
     टेंपरेचर
    0.42
    POSITIVE LOGITS
     <?
    0.50
     शुर
    0.46
     {\
    0.46
    '],
    0.45
    here
    0.45
     \'
    0.45
    धिकारिक
    0.44
     "`
    0.44
     ''
    0.44
     "
    0.42
    Act Density 0.000%

    No Known Activations