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

    Neuronpedia

    INDEX
    Explanations

    percentage, investor, density, round breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     가게
    1.22
     kiles
    1.21
     daimyo
    1.20
     FabD
    1.18
     ejemplos
    1.16
     barium
    1.16
    ⟥
    1.15
     эш
    1.14
    <0xA8>
    1.14
     copyrights
    1.13
    POSITIVE LOGITS
    ال
    1.04
    y
    1.02
    om
    1.01
    al
    0.99
    ืน
    0.96
    an
    0.96
    Land
    0.95
    o
    0.95
    State
    0.94
    robi
    0.93
    Act Density 0.001%

    No Known Activations