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

    Neuronpedia

    INDEX
    Explanations

    calculations with units and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ཊ
    0.50
    ස්ට
    0.49
    Biology
    0.48
    隧
    0.48
    缙
    0.48
    ṑ
    0.48
     pérd
    0.47
     услуг
    0.47
    蒎
    0.47
     précédente
    0.47
    POSITIVE LOGITS
     if
    0.51
     If
    0.47
     re
    0.46
     (
    0.46
    </td>
    0.46
     Its
    0.46
         
    0.46
          
    0.45
     or
    0.45
    ’
    0.45
    Act Density 0.024%

    No Known Activations