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

    Neuronpedia

    INDEX
    Explanations

    but other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neurolog
    0.46
     uphe
    0.44
     officially
    0.42
     ortodox
    0.41
    waitForIdleSync
    0.41
     totalitarian
    0.41
     salari
    0.40
     orthodox
    0.40
     tarixində
    0.40
     probably
    0.40
    POSITIVE LOGITS
    인
    0.46
    Grilled
    0.45
    轻松
    0.45
    Explore
    0.44
    Control
    0.44
     Grilled
    0.44
    部件
    0.43
    配件
    0.43
    AspectRatio
    0.43
    构
    0.43
    Act Density 0.013%

    No Known Activations