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

    Neuronpedia

    INDEX
    Explanations

    determiners followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $\
    1.74
    y
    1.70
    ுங்கள்
    1.67
    est
    1.66
    bounce
    1.64
    hip
    1.60
     করিয়াছিল
    1.57
     empate
    1.57
    ities
    1.48
    Ве
    1.48
    POSITIVE LOGITS
     yüzden
    2.27
    ্যান্ড
    2.00
     sifat
    1.99
    ാഗ
    1.87
    ডস
    1.86
    elton
    1.85
    ampe
    1.81
    <bos>
    1.81
     које
    1.80
     nedenle
    1.77
    Act Density 0.279%

    No Known Activations