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

    Neuronpedia

    INDEX
    Explanations

    slow down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Up
    -0.11
     upward
    -0.11
    _upd
    -0.10
     Ups
    -0.10
    OrDefault
    -0.09
    Ups
    -0.09
    .Up
    -0.09
    åºķ
    -0.09
     esac
    -0.09
     upt
    -0.09
    POSITIVE LOGITS
     down
    1.05
    down
    0.73
    -down
    0.71
     DOWN
    0.64
    Down
    0.61
     Down
    0.59
     xuá»ijng
    0.57
    _down
    0.55
    DOWN
    0.52
    ä¸ĭæĿ¥
    0.51
    Act Density 0.076%

    No Known Activations