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

    Neuronpedia

    INDEX
    Explanations

    SUVs and vehicle types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    された
    0.58
    ابه
    0.55
    ্যান্ড
    0.54
    戏剧
    0.52
    尺度
    0.51
    aceted
    0.50
    اق
    0.50
    兒子
    0.50
    </h4>
    0.49
    tho
    0.49
    POSITIVE LOGITS
     will
    0.65
     those
    0.64
     suffoc
    0.64
     adventurous
    0.62
     adventure
    0.62
     stopping
    0.62
     feeling
    0.61
     ph
    0.60
    岂
    0.60
     worry
    0.60
    Act Density 0.053%

    No Known Activations