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

    Neuronpedia

    INDEX
    Explanations

    at odds with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಇದೆ
    0.48
     fateful
    0.45
     ಬಹಳ
    0.43
    鄙
    0.43
     காட்சி
    0.42
    <unused64>
    0.41
     बेहद
    0.41
     これらの
    0.41
     संभावित
    0.40
    澈
    0.40
    POSITIVE LOGITS
     temporarily
    0.48
     crews
    0.44
     bees
    0.43
     flange
    0.42
     temporary
    0.42
     functioning
    0.42
     output
    0.41
     elves
    0.41
    v
    0.41
    nellement
    0.40
    Act Density 0.003%

    No Known Activations