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

    Neuronpedia

    INDEX
    Explanations

    date, intent, types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сериа
    0.52
    네
    0.52
     encuentro
    0.51
    نه
    0.51
    ﻛ
    0.49
    给
    0.48
    ک
    0.48
     secondo
    0.47
    लोक
    0.47
     encuentros
    0.47
    POSITIVE LOGITS
    ='')
    0.43
     deforestation
    0.42
     নাই
    0.42
    ಿತಿ
    0.42
    矨
    0.41
    </h6>
    0.41
     ／
    0.41
     poor
    0.41
     ‘’
    0.41
    [-]
    0.41
    Act Density 0.000%

    No Known Activations