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

    Neuronpedia

    INDEX
    Explanations

    lampshade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     машину
    0.40
    ເຄື່ອງ
    0.39
     камер
    0.39
    DropdownBox
    0.38
    ächen
    0.38
    ヤモンド
    0.37
     Conta
    0.37
     Pach
    0.37
     निपटने
    0.36
    ନ୍ତି
    0.36
    POSITIVE LOGITS
     shade
    0.70
    hade
    0.66
     posts
    0.63
     Shade
    0.63
     shades
    0.63
    stand
    0.62
     wick
    0.57
    shade
    0.57
    wick
    0.56
     Shades
    0.55
    Act Density 0.005%

    No Known Activations