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

    Neuronpedia

    INDEX
    Explanations

    block and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人数
    0.77
    蓍
    0.71
     شخص
    0.65
    启发
    0.63
    寇
    0.62
    ೂ
    0.62
    Paper
    0.62
    randomIndex
    0.62
    ノル
    0.61
     নৌকা
    0.61
    POSITIVE LOGITS
     block
    3.15
     blocks
    2.95
    block
    2.88
    Block
    2.81
     Block
    2.72
     Blocks
    2.66
    ブロック
    2.62
    blocks
    2.55
    Blocks
    2.54
     bloco
    2.54
    Act Density 1.003%

    No Known Activations