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

    Neuronpedia

    INDEX
    Explanations

    both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്തിനെ
    0.34
    ிலும்
    0.34
     दिलीप
    0.33
    匏
    0.33
     implique
    0.33
    '>{
    0.33
     nörd
    0.33
    <unused664>
    0.32
     नीतीश
    0.32
    謊
    0.32
    POSITIVE LOGITS
     entrambi
    0.54
     ambos
    0.51
     beide
    0.50
     begge
    0.48
     উভয়
    0.46
     together
    0.45
    这两
    0.45
     दोनों
    0.44
    Both
    0.44
     both
    0.43
    Act Density 0.429%

    No Known Activations