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

    Neuronpedia

    INDEX
    Explanations

    quantization levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вати
    0.54
     ਜਾਂ
    0.48
    뿜
    0.47
    ７
    0.47
    农民
    0.46
    Сред
    0.44
    ті
    0.43
    èrement
    0.43
    ків
    0.43
    ژی
    0.43
    POSITIVE LOGITS
     resonates
    0.55
     improved
    0.52
     ensures
    0.51
     improves
    0.50
     appr
    0.49
     shows
    0.49
     Ethiopia
    0.48
     menu
    0.48
     during
    0.48
     PTFE
    0.48
    Act Density 0.006%

    No Known Activations