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

    Neuronpedia

    INDEX
    Explanations

    launch, ceremony, reduce, man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adin
    0.52
    峤
    0.47
    Rl
    0.44
    心的
    0.43
    LOTRE
    0.43
     Painlev
    0.43
    ޟ
    0.42
     kalau
    0.42
     sluč
    0.42
    చేసిన
    0.42
    POSITIVE LOGITS
    0.62
     launch
    0.51
    י
    0.48
     require
    0.47
    用
    0.46
     launches
    0.46
    ，
    0.46
     запуска
    0.45
     requires
    0.44
     with
    0.43
    Act Density 0.003%

    No Known Activations