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

    Neuronpedia

    INDEX
    Explanations

    brick wall and brick by brick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    刮
    0.79
     Fres
    0.77
    소
    0.76
     प्रमोद
    0.73
    Few
    0.73
    قبال
    0.72
     winner
    0.72
    Cô
    0.72
     Few
    0.71
    ます
    0.70
    POSITIVE LOGITS
    laying
    1.42
    layers
    1.31
    layer
    1.29
    bats
    1.15
     veneer
    1.09
    work
    1.05
     paved
    1.05
     paving
    1.03
     masonry
    1.02
    砌
    1.00
    Act Density 0.004%

    No Known Activations