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

    Neuronpedia

    INDEX
    Explanations

    remote control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জোট
    0.48
     зависимости
    0.48
     ছত্র
    0.47
     претен
    0.45
    Gallery
    0.44
     richt
    0.44
     বাঁচাতে
    0.44
    Celebr
    0.43
     помогут
    0.43
    Base
    0.43
    POSITIVE LOGITS
     usaha
    0.47
     actos
    0.44
    osaurus
    0.43
    oirs
    0.43
    海水
    0.42
    experiments
    0.40
     व्याकरण
    0.40
    癸
    0.40
    𝑌
    0.40
    畜
    0.40
    Act Density 0.028%

    No Known Activations