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

    Neuronpedia

    INDEX
    Explanations

    code delimiters or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    će
    0.78
     પોતા
    0.71
     pensez
    0.70
    શે
    0.68
     তাহাকে
    0.67
    人们
    0.66
    学家
    0.66
     Среди
    0.65
     keyst
    0.65
     Republike
    0.65
    POSITIVE LOGITS
    e
    0.87
    ot
    0.87
    шением
    0.85
    mnt
    0.85
    csv
    0.81
    мых
    0.80
     WAT
    0.80
     añadir
    0.79
     investigar
    0.79
    atán
    0.78
    Act Density 0.000%

    No Known Activations