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

    Neuronpedia

    INDEX
    Explanations

    stop then action or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ale
    0.40
    MAL
    0.38
            
    0.37
     Jackson
    0.36
     HDL
    0.36
     Vak
    0.35
    Offline
    0.35
     matéri
    0.35
    Kon
    0.35
     Wilkinson
    0.35
    POSITIVE LOGITS
     stopped
    0.89
     Stopped
    0.86
     Stop
    0.85
     STOP
    0.84
     Stopping
    0.83
     stop
    0.82
     dừng
    0.82
    Stop
    0.81
     stopp
    0.80
    stop
    0.80
    Act Density 0.016%

    No Known Activations