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

    Neuronpedia

    INDEX
    Explanations

    improving user experience or service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     domicilio
    0.39
    ENAME
    0.39
     Minimal
    0.38
     Name
    0.38
    Minimal
    0.38
     Protected
    0.37
     Disclosure
    0.37
     contatt
    0.36
    痂
    0.36
     IP
    0.36
    POSITIVE LOGITS
     improve
    0.85
     melhorar
    0.85
     verbeter
    0.81
     améliorer
    0.80
     improving
    0.79
     improves
    0.79
     개선
    0.78
     улуч
    0.77
     mejorar
    0.75
     verbessern
    0.75
    Act Density 0.003%

    No Known Activations