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

    Neuronpedia

    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ılar
    0.41
    而在
    0.40
    事で
    0.40
    坵
    0.40
     Marc
    0.39
    穢
    0.38
    幄
    0.38
     মৌলিক
    0.38
     Tổ
    0.38
    ออก
    0.37
    POSITIVE LOGITS
    Boost
    0.41
     Verme
    0.39
    Sunglasses
    0.37
    FR
    0.37
     fud
    0.37
    Valve
    0.36
    Maintain
    0.36
     pesante
    0.36
     își
    0.35
     кін
    0.35
    Act Density 0.628%

    No Known Activations