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

    Neuronpedia

    INDEX
    Explanations

    html/css ui components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kıs
    0.34
    恪
    0.30
     العمل
    0.30
    ณ์
    0.30
     生命
    0.30
    αιν
    0.30
    猶
    0.30
    城堡
    0.29
     vésicules
    0.29
    很久
    0.29
    POSITIVE LOGITS
    btn
    0.54
    clearfix
    0.53
    ui
    0.52
    container
    0.51
    uk
    0.50
    mui
    0.47
     btn
    0.45
    mt
    0.45
    row
    0.44
     container
    0.44
    Act Density 0.005%

    No Known Activations