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

    Neuronpedia

    INDEX
    Explanations

    step-by-step explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வைகள்
    0.76
    ೀರ್
    0.75
     Gres
    0.72
     कहकर
    0.68
    Across
    0.66
     معه
    0.66
     exo
    0.66
     ट्रॉप
    0.65
     wrink
    0.65
     लगाते
    0.65
    POSITIVE LOGITS
     bu
    1.22
     buy
    1.22
     be
    1.13
     b
    1.12
     hy
    1.07
    hy
    1.03
     my
    1.01
    buy
    1.00
     bi
    0.95
     bt
    0.94
    Act Density 0.181%

    No Known Activations