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

    Neuronpedia

    INDEX
    Explanations

    Stability AI and Reboot Nation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PO
    0.40
    Stra
    0.38
    Nam
    0.35
    الط
    0.35
    Res
    0.34
    portion
    0.34
    resc
    0.34
     nautical
    0.34
    plify
    0.33
    along
    0.33
    POSITIVE LOGITS
    游戏的
    0.45
    ؔ
    0.43
    গণের
    0.41
    怀疑
    0.40
    ळ्या
    0.40
     নামক
    0.40
    মূলক
    0.39
    乐队
    0.39
    ่อง
    0.39
    と呼ばれる
    0.38
    Act Density 0.023%

    No Known Activations