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

    Neuronpedia

    INDEX
    Explanations

    stop action or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.64
    สู่
    0.54
    ;}
    0.50
    Otro
    0.49
    0.49
    )];
    0.48
    ীর্ণ
    0.48
    ي
    0.48
    ,’
    0.48
    ่
    0.48
    POSITIVE LOGITS
     Stopping
    1.09
    停止
    1.07
     stopping
    1.06
     Stop
    1.05
     stopped
    1.04
     stop
    1.02
    stop
    1.02
     dừng
    1.02
    止
    1.02
    stopping
    1.01
    Act Density 0.027%

    No Known Activations