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

    Neuronpedia

    INDEX
    Explanations

    history breeds distrust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Acquisitions
    0.49
     international
    0.44
     internationalen
    0.44
     mancan
    0.42
     উন্নয়নে
    0.41
     professional
    0.40
     HR
    0.40
     consulting
    0.39
     DA
    0.39
     Professional
    0.39
    POSITIVE LOGITS
     overthrown
    0.49
     تشدد
    0.45
    废物
    0.45
    𝓻
    0.45
    ⛰
    0.42
     开始
    0.42
    HasFieldError
    0.42
    惭
    0.41
     hiçbir
    0.40
    UpSync
    0.40
    Act Density 0.012%

    No Known Activations