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

    Neuronpedia

    INDEX
    Explanations

    outages and malfunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biosynthesis
    0.50
     TYPES
    0.49
     textiles
    0.48
     argparse
    0.48
     inscrib
    0.48
     kompos
    0.47
     transformasi
    0.47
     Transform
    0.47
     padx
    0.47
     rescaling
    0.46
    POSITIVE LOGITS
     outage
    1.08
     outages
    1.08
     malfunction
    0.99
     malfunctions
    0.98
     glitch
    0.94
     malfunctioning
    0.94
     glitches
    0.91
    故障
    0.91
     reliability
    0.80
     failures
    0.79
    Act Density 0.139%

    No Known Activations