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

    Neuronpedia

    INDEX
    Explanations

    additional and other features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Documentation
    -0.09
    游戏副本
    -0.07
     Sudoku
    -0.07
    _wr
    -0.07
    zet
    -0.07
    Packages
    -0.06
    Girl
    -0.06
    .staff
    -0.06
     vẽ
    -0.06
    _lv
    -0.06
    POSITIVE LOGITS
    个交易
    0.07
    탰
    0.07
    なくなった
    0.07
     humano
    0.06
    โน
    0.06
    לי
    0.06
    うま
    0.06
    $log
    0.06
    .tmp
    0.06
    .init
    0.06
    Act Density 0.155%

    No Known Activations