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

    Neuronpedia

    INDEX
    Explanations

    along the way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    1.41
     materialistic
    1.07
    𝘶
    1.02
    ুদ
    1.00
    гель
    0.96
    ность
    0.96
    ελ
    0.95
    ኋላ
    0.95
     surrounding
    0.94
     materialism
    0.94
    POSITIVE LOGITS
    shore
    1.36
     zatim
    1.35
    tudo
    1.30
    দীন
    1.24
    path
    1.22
     highways
    1.17
    along
    1.17
    ੀ
    1.17
     contours
    1.17
    road
    1.16
    Act Density 0.034%

    No Known Activations